--- name: categorization_golden_v2 description: Golden dataset for transaction categorization evaluation with US and European merchants eval_type: categorization version: "2.0" metadata: created_at: "2025-12-04" updated_at: "2025-12-04" source: manual_curation notes: | Difficulty levels: - easy: Unambiguous merchant names, single clear category - medium: Requires domain knowledge but has clear answer - hard: Genuinely ambiguous, multiple reasonable interpretations - edge_case: Should return null (generic/cryptic descriptions) This v2 dataset includes: - 200 total samples (150 base + 50 challenging) - US merchants (original) - European merchants (UK, Germany, France, Spain, Italy, Netherlands, etc.) - Mix of international and regional brands - Challenging samples: local businesses, abbreviations, cryptic formats - More ambiguous cases requiring nuanced reasoning context: categories: - id: "income" name: "Income" classification: "income" is_subcategory: false - id: "salary" name: "Salary" classification: "income" is_subcategory: true parent_id: "income" - id: "food_and_drink" name: "Food & Drink" classification: "expense" is_subcategory: false - id: "restaurants" name: "Restaurants" classification: "expense" is_subcategory: true parent_id: "food_and_drink" - id: "groceries" name: "Groceries" classification: "expense" is_subcategory: true parent_id: "food_and_drink" - id: "coffee_shops" name: "Coffee Shops" classification: "expense" is_subcategory: true parent_id: "food_and_drink" - id: "shopping" name: "Shopping" classification: "expense" is_subcategory: false - id: "clothing" name: "Clothing" classification: "expense" is_subcategory: true parent_id: "shopping" - id: "electronics" name: "Electronics" classification: "expense" is_subcategory: true parent_id: "shopping" - id: "transportation" name: "Transportation" classification: "expense" is_subcategory: false - id: "gas" name: "Gas & Fuel" classification: "expense" is_subcategory: true parent_id: "transportation" - id: "rideshare" name: "Rideshare" classification: "expense" is_subcategory: true parent_id: "transportation" - id: "public_transit" name: "Public Transit" classification: "expense" is_subcategory: true parent_id: "transportation" - id: "entertainment" name: "Entertainment" classification: "expense" is_subcategory: false - id: "streaming" name: "Streaming Services" classification: "expense" is_subcategory: true parent_id: "entertainment" - id: "utilities" name: "Utilities" classification: "expense" is_subcategory: false - id: "housing" name: "Housing" classification: "expense" is_subcategory: false - id: "rent" name: "Rent" classification: "expense" is_subcategory: true parent_id: "housing" - id: "health" name: "Health & Wellness" classification: "expense" is_subcategory: false - id: "pharmacy" name: "Pharmacy" classification: "expense" is_subcategory: true parent_id: "health" - id: "gym" name: "Gym & Fitness" classification: "expense" is_subcategory: true parent_id: "health" - id: "travel" name: "Travel" classification: "expense" is_subcategory: false - id: "flights" name: "Flights" classification: "expense" is_subcategory: true parent_id: "travel" - id: "hotels" name: "Hotels" classification: "expense" is_subcategory: true parent_id: "travel" - id: "subscriptions" name: "Subscriptions" classification: "expense" is_subcategory: false - id: "personal_care" name: "Personal Care" classification: "expense" is_subcategory: false - id: "gifts" name: "Gifts & Donations" classification: "expense" is_subcategory: false samples: # ============================================================================= # EASY SAMPLES - US Merchants (40 samples) # ============================================================================= # Food & Drink - US - id: cat_v2_easy_001 difficulty: easy tags: [food_and_drink, us, clear_merchant] input: id: txn_v2_001 amount: 12.99 classification: expense description: "MCDONALD'S #12345 SPRINGFIELD IL" expected: category_name: "Food & Drink" acceptable_alternatives: ["Restaurants"] - id: cat_v2_easy_002 difficulty: easy tags: [food_and_drink, us, clear_merchant] input: id: txn_v2_002 amount: 8.50 classification: expense description: "BURGER KING #456 NEW YORK NY" expected: category_name: "Food & Drink" acceptable_alternatives: ["Restaurants"] - id: cat_v2_easy_003 difficulty: easy tags: [food_and_drink, us, clear_merchant] input: id: txn_v2_003 amount: 9.99 classification: expense description: "TACO BELL #789" expected: category_name: "Food & Drink" acceptable_alternatives: ["Restaurants"] - id: cat_v2_easy_004 difficulty: easy tags: [food_and_drink, us, clear_merchant] input: id: txn_v2_004 amount: 14.99 classification: expense description: "CHIPOTLE MEXICAN GRILL" expected: category_name: "Food & Drink" acceptable_alternatives: ["Restaurants"] - id: cat_v2_easy_005 difficulty: easy tags: [food_and_drink, us, clear_merchant] input: id: txn_v2_005 amount: 8.99 classification: expense description: "WENDY'S #5678" expected: category_name: "Food & Drink" acceptable_alternatives: ["Restaurants"] # Coffee Shops - US - id: cat_v2_easy_006 difficulty: easy tags: [coffee_shops, us, clear_merchant] input: id: txn_v2_006 amount: 5.75 classification: expense description: "STARBUCKS STORE #9876" expected: category_name: "Coffee Shops" - id: cat_v2_easy_007 difficulty: easy tags: [coffee_shops, us, clear_merchant] input: id: txn_v2_007 amount: 4.25 classification: expense description: "DUNKIN #12345" expected: category_name: "Coffee Shops" - id: cat_v2_easy_008 difficulty: easy tags: [coffee_shops, us, clear_merchant] input: id: txn_v2_008 amount: 6.50 classification: expense description: "PEETS COFFEE #456" expected: category_name: "Coffee Shops" # Groceries - US - id: cat_v2_easy_009 difficulty: easy tags: [groceries, us, clear_merchant] input: id: txn_v2_009 amount: 156.32 classification: expense description: "WHOLE FOODS MKT #10234" expected: category_name: "Groceries" - id: cat_v2_easy_010 difficulty: easy tags: [groceries, us, clear_merchant] input: id: txn_v2_010 amount: 87.45 classification: expense description: "TRADER JOE'S #567 LOS ANGELES" expected: category_name: "Groceries" - id: cat_v2_easy_011 difficulty: easy tags: [groceries, us, clear_merchant] input: id: txn_v2_011 amount: 98.34 classification: expense description: "PUBLIX SUPER MARKET" expected: category_name: "Groceries" - id: cat_v2_easy_012 difficulty: easy tags: [groceries, us, clear_merchant] input: id: txn_v2_012 amount: 67.89 classification: expense description: "KROGER #789 GROCERY" expected: category_name: "Groceries" # Gas & Fuel - US - id: cat_v2_easy_013 difficulty: easy tags: [gas, us, clear_merchant] input: id: txn_v2_013 amount: 45.00 classification: expense description: "SHELL OIL 573849234" expected: category_name: "Gas & Fuel" - id: cat_v2_easy_014 difficulty: easy tags: [gas, us, clear_merchant] input: id: txn_v2_014 amount: 52.30 classification: expense description: "CHEVRON STATION #1234" expected: category_name: "Gas & Fuel" - id: cat_v2_easy_015 difficulty: easy tags: [gas, us, clear_merchant] input: id: txn_v2_015 amount: 48.50 classification: expense description: "EXXONMOBIL 12345" expected: category_name: "Gas & Fuel" # Rideshare - US - id: cat_v2_easy_016 difficulty: easy tags: [rideshare, us, clear_merchant] input: id: txn_v2_016 amount: 23.50 classification: expense description: "UBER *TRIP HELP.UBER.COM" expected: category_name: "Rideshare" - id: cat_v2_easy_017 difficulty: easy tags: [rideshare, us, clear_merchant] input: id: txn_v2_017 amount: 18.75 classification: expense description: "LYFT *RIDE SAT 7PM" expected: category_name: "Rideshare" # Streaming - US - id: cat_v2_easy_018 difficulty: easy tags: [streaming, us, clear_merchant] input: id: txn_v2_018 amount: 15.99 classification: expense description: "NETFLIX.COM" expected: category_name: "Streaming Services" acceptable_alternatives: ["Subscriptions"] - id: cat_v2_easy_019 difficulty: easy tags: [streaming, us, clear_merchant] input: id: txn_v2_019 amount: 10.99 classification: expense description: "SPOTIFY USA" expected: category_name: "Streaming Services" acceptable_alternatives: ["Subscriptions"] # Electronics - US - id: cat_v2_easy_020 difficulty: easy tags: [electronics, us, clear_merchant] input: id: txn_v2_020 amount: 299.99 classification: expense description: "BEST BUY 00000456" expected: category_name: "Electronics" acceptable_alternatives: ["Shopping"] # Clothing - US - id: cat_v2_easy_021 difficulty: easy tags: [clothing, us, clear_merchant] input: id: txn_v2_021 amount: 89.99 classification: expense description: "GAP STORE #1234" expected: category_name: "Clothing" acceptable_alternatives: ["Shopping"] - id: cat_v2_easy_022 difficulty: easy tags: [clothing, us, clear_merchant] input: id: txn_v2_022 amount: 65.00 classification: expense description: "OLD NAVY #567" expected: category_name: "Clothing" acceptable_alternatives: ["Shopping"] # Pharmacy - US - id: cat_v2_easy_023 difficulty: easy tags: [pharmacy, us, clear_merchant] input: id: txn_v2_023 amount: 24.99 classification: expense description: "CVS/PHARMACY #4567" expected: category_name: "Pharmacy" - id: cat_v2_easy_024 difficulty: easy tags: [pharmacy, us, clear_merchant] input: id: txn_v2_024 amount: 35.50 classification: expense description: "WALGREENS #12345" expected: category_name: "Pharmacy" acceptable_alternatives: ["Health & Wellness"] # Gym - US - id: cat_v2_easy_025 difficulty: easy tags: [gym, us, clear_merchant] input: id: txn_v2_025 amount: 39.99 classification: expense description: "PLANET FITNESS MONTHLY" expected: category_name: "Gym & Fitness" # Flights - US - id: cat_v2_easy_026 difficulty: easy tags: [flights, us, clear_merchant] input: id: txn_v2_026 amount: 345.00 classification: expense description: "UNITED AIRLINES 0162345678" expected: category_name: "Flights" acceptable_alternatives: ["Travel"] - id: cat_v2_easy_027 difficulty: easy tags: [flights, us, clear_merchant] input: id: txn_v2_027 amount: 456.00 classification: expense description: "DELTA AIR LINES" expected: category_name: "Flights" acceptable_alternatives: ["Travel"] # Hotels - US - id: cat_v2_easy_028 difficulty: easy tags: [hotels, us, clear_merchant] input: id: txn_v2_028 amount: 189.00 classification: expense description: "MARRIOTT HOTELS NYC" expected: category_name: "Hotels" - id: cat_v2_easy_029 difficulty: easy tags: [hotels, us, clear_merchant] input: id: txn_v2_029 amount: 245.00 classification: expense description: "HILTON HOTELS" expected: category_name: "Hotels" # Income - US - id: cat_v2_easy_030 difficulty: easy tags: [income, salary, us, clear_merchant] input: id: txn_v2_030 amount: 3500.00 classification: income description: "ACME CORP PAYROLL" expected: category_name: "Salary" - id: cat_v2_easy_031 difficulty: easy tags: [income, salary, us, clear_merchant] input: id: txn_v2_031 amount: 2800.00 classification: income description: "DIRECT DEPOSIT - PAYROLL" expected: category_name: "Salary" # ============================================================================= # EASY SAMPLES - European Merchants (20 samples) # ============================================================================= # Food & Drink - Europe - id: cat_v2_easy_eu_001 difficulty: easy tags: [food_and_drink, europe, uk, clear_merchant] input: id: txn_v2_eu_001 amount: 8.99 classification: expense description: "NANDO'S LONDON" expected: category_name: "Food & Drink" acceptable_alternatives: ["Restaurants"] - id: cat_v2_easy_eu_002 difficulty: easy tags: [food_and_drink, europe, uk, clear_merchant] input: id: txn_v2_eu_002 amount: 6.50 classification: expense description: "GREGGS PLC" expected: category_name: "Food & Drink" - id: cat_v2_easy_eu_003 difficulty: easy tags: [food_and_drink, europe, germany, clear_merchant] input: id: txn_v2_eu_003 amount: 7.80 classification: expense description: "NORDSEE GMBH BERLIN" expected: category_name: "Food & Drink" acceptable_alternatives: ["Food & Drink"] # Coffee Shops - Europe - id: cat_v2_easy_eu_004 difficulty: easy tags: [coffee_shops, europe, uk, clear_merchant] input: id: txn_v2_eu_004 amount: 4.50 classification: expense description: "COSTA COFFEE LTD" expected: category_name: "Coffee Shops" - id: cat_v2_easy_eu_005 difficulty: easy tags: [coffee_shops, europe, uk, clear_merchant] input: id: txn_v2_eu_005 amount: 3.80 classification: expense description: "CAFFE NERO GROUP" expected: category_name: "Coffee Shops" - id: cat_v2_easy_eu_006 difficulty: easy tags: [coffee_shops, europe, netherlands, clear_merchant] input: id: txn_v2_eu_006 amount: 4.20 classification: expense description: "STARBUCKS AMSTERDAM" expected: category_name: "Coffee Shops" # Groceries - Europe - id: cat_v2_easy_eu_007 difficulty: easy tags: [groceries, europe, uk, clear_merchant] input: id: txn_v2_eu_007 amount: 87.50 classification: expense description: "TESCO STORES LTD" expected: category_name: "Groceries" - id: cat_v2_easy_eu_008 difficulty: easy tags: [groceries, europe, uk, clear_merchant] input: id: txn_v2_eu_008 amount: 65.30 classification: expense description: "SAINSBURY'S SUPERMARKET" expected: category_name: "Groceries" - id: cat_v2_easy_eu_009 difficulty: easy tags: [groceries, europe, germany, clear_merchant] input: id: txn_v2_eu_009 amount: 78.90 classification: expense description: "LIDL DIENSTLEISTUNG" expected: category_name: "Groceries" - id: cat_v2_easy_eu_010 difficulty: easy tags: [groceries, europe, germany, clear_merchant] input: id: txn_v2_eu_010 amount: 92.40 classification: expense description: "ALDI SUED GMBH" expected: category_name: "Groceries" - id: cat_v2_easy_eu_011 difficulty: easy tags: [groceries, europe, france, clear_merchant] input: id: txn_v2_eu_011 amount: 123.50 classification: expense description: "CARREFOUR MARKET PARIS" expected: category_name: "Groceries" - id: cat_v2_easy_eu_012 difficulty: easy tags: [groceries, europe, netherlands, clear_merchant] input: id: txn_v2_eu_012 amount: 67.80 classification: expense description: "ALBERT HEIJN BV" expected: category_name: "Groceries" # Gas & Fuel - Europe - id: cat_v2_easy_eu_013 difficulty: easy tags: [gas, europe, uk, clear_merchant] input: id: txn_v2_eu_013 amount: 75.00 classification: expense description: "BP OIL UK LTD" expected: category_name: "Gas & Fuel" - id: cat_v2_easy_eu_014 difficulty: easy tags: [gas, europe, france, clear_merchant] input: id: txn_v2_eu_014 amount: 68.50 classification: expense description: "TOTAL ENERGIES PARIS" expected: category_name: "Gas & Fuel" # Flights - Europe - id: cat_v2_easy_eu_015 difficulty: easy tags: [flights, europe, uk, clear_merchant] input: id: txn_v2_eu_015 amount: 189.00 classification: expense description: "BRITISH AIRWAYS PLC" expected: category_name: "Flights" acceptable_alternatives: ["Travel"] - id: cat_v2_easy_eu_016 difficulty: easy tags: [flights, europe, ireland, clear_merchant] input: id: txn_v2_eu_016 amount: 89.99 classification: expense description: "RYANAIR DAC" expected: category_name: "Flights" acceptable_alternatives: ["Travel"] - id: cat_v2_easy_eu_017 difficulty: easy tags: [flights, europe, germany, clear_merchant] input: id: txn_v2_eu_017 amount: 245.00 classification: expense description: "LUFTHANSA AG FRANKFURT" expected: category_name: "Flights" acceptable_alternatives: ["Travel"] - id: cat_v2_easy_eu_018 difficulty: easy tags: [flights, europe, france, clear_merchant] input: id: txn_v2_eu_018 amount: 198.00 classification: expense description: "AIR FRANCE KLM" expected: category_name: "Flights" acceptable_alternatives: ["Travel"] # Clothing - Europe - id: cat_v2_easy_eu_019 difficulty: easy tags: [clothing, europe, spain, clear_merchant] input: id: txn_v2_eu_019 amount: 79.99 classification: expense description: "ZARA ESPANA SA" expected: category_name: "Clothing" acceptable_alternatives: ["Shopping"] - id: cat_v2_easy_eu_020 difficulty: easy tags: [clothing, europe, sweden, clear_merchant] input: id: txn_v2_eu_020 amount: 45.00 classification: expense description: "H&M HENNES MAURITZ AB" expected: category_name: "Clothing" acceptable_alternatives: ["Shopping"] # ============================================================================= # MEDIUM SAMPLES - US Merchants (25 samples) # ============================================================================= # Restaurants - US - id: cat_v2_med_001 difficulty: medium tags: [restaurants, us, chain] input: id: txn_v2_med_001 amount: 67.50 classification: expense description: "OLIVE GARDEN #456" expected: category_name: "Restaurants" - id: cat_v2_med_002 difficulty: medium tags: [restaurants, us, chain] input: id: txn_v2_med_002 amount: 85.00 classification: expense description: "CHEESECAKE FACTORY" expected: category_name: "Restaurants" - id: cat_v2_med_003 difficulty: medium tags: [restaurants, us, upscale] input: id: txn_v2_med_003 amount: 123.45 classification: expense description: "RUTH'S CHRIS STEAK" expected: category_name: "Restaurants" # Groceries - Warehouse - id: cat_v2_med_004 difficulty: medium tags: [groceries, us, warehouse] input: id: txn_v2_med_004 amount: 234.56 classification: expense description: "COSTCO WHSE #1234" expected: category_name: "Groceries" acceptable_alternatives: ["Shopping"] - id: cat_v2_med_005 difficulty: medium tags: [groceries, us, warehouse] input: id: txn_v2_med_005 amount: 178.90 classification: expense description: "SAM'S CLUB #8765" expected: category_name: "Groceries" acceptable_alternatives: ["Shopping"] # Utilities - US - id: cat_v2_med_006 difficulty: medium tags: [utilities, us, power] input: id: txn_v2_med_006 amount: 125.00 classification: expense description: "CON EDISON PAYMENT" expected: category_name: "Utilities" - id: cat_v2_med_007 difficulty: medium tags: [utilities, us, power] input: id: txn_v2_med_007 amount: 89.00 classification: expense description: "PACIFIC GAS ELEC CO" expected: category_name: "Utilities" - id: cat_v2_med_008 difficulty: medium tags: [utilities, us, internet] input: id: txn_v2_med_008 amount: 145.00 classification: expense description: "XFINITY INTERNET" expected: category_name: "Utilities" acceptable_alternatives: ["Subscriptions"] - id: cat_v2_med_009 difficulty: medium tags: [utilities, us, phone] input: id: txn_v2_med_009 amount: 89.00 classification: expense description: "AT&T WIRELESS" expected: category_name: "Utilities" acceptable_alternatives: ["Subscriptions"] # Public Transit - US - id: cat_v2_med_010 difficulty: medium tags: [public_transit, us] input: id: txn_v2_med_010 amount: 127.00 classification: expense description: "MTA *METROCARD" expected: category_name: "Public Transit" acceptable_alternatives: ["Transportation"] - id: cat_v2_med_011 difficulty: medium tags: [public_transit, us] input: id: txn_v2_med_011 amount: 2.75 classification: expense description: "WMATA SMARTRIP" expected: category_name: "Public Transit" acceptable_alternatives: ["Transportation"] # Housing - US - id: cat_v2_med_012 difficulty: medium tags: [rent, us, housing] input: id: txn_v2_med_012 amount: 2100.00 classification: expense description: "AVALON APARTMENTS RENT" expected: category_name: "Rent" acceptable_alternatives: ["Housing"] # Subscriptions - US - id: cat_v2_med_013 difficulty: medium tags: [subscriptions, us] input: id: txn_v2_med_013 amount: 9.99 classification: expense description: "APPLE.COM/BILL" expected: category_name: "Subscriptions" - id: cat_v2_med_014 difficulty: medium tags: [subscriptions, us] input: id: txn_v2_med_014 amount: 2.99 classification: expense description: "GOOGLE *STORAGE" expected: category_name: "Subscriptions" # Personal Care - US - id: cat_v2_med_015 difficulty: medium tags: [personal_care, us] input: id: txn_v2_med_015 amount: 45.00 classification: expense description: "SUPERCUTS #1234" expected: category_name: "Personal Care" - id: cat_v2_med_016 difficulty: medium tags: [personal_care, us] input: id: txn_v2_med_016 amount: 85.00 classification: expense description: "ULTA BEAUTY #567" expected: category_name: "Personal Care" acceptable_alternatives: ["Shopping"] # Gifts & Donations - US - id: cat_v2_med_017 difficulty: medium tags: [gifts, us, donation] input: id: txn_v2_med_017 amount: 50.00 classification: expense description: "RED CROSS DONATION" expected: category_name: "Gifts & Donations" - id: cat_v2_med_018 difficulty: medium tags: [gifts, us, donation] input: id: txn_v2_med_018 amount: 100.00 classification: expense description: "UNICEF USA" expected: category_name: "Gifts & Donations" # Entertainment - US - id: cat_v2_med_019 difficulty: medium tags: [entertainment, us, movies] input: id: txn_v2_med_019 amount: 45.00 classification: expense description: "AMC THEATRES #1234" expected: category_name: "Entertainment" - id: cat_v2_med_020 difficulty: medium tags: [entertainment, us, tickets] input: id: txn_v2_med_020 amount: 89.00 classification: expense description: "TICKETMASTER *EVENT" expected: category_name: "Entertainment" # Travel - US - id: cat_v2_med_021 difficulty: medium tags: [travel, us, car_rental] input: id: txn_v2_med_021 amount: 156.00 classification: expense description: "HERTZ RENT-A-CAR" expected: category_name: "Travel" acceptable_alternatives: ["Transportation"] - id: cat_v2_med_022 difficulty: medium tags: [hotels, us, lodging] input: id: txn_v2_med_022 amount: 234.00 classification: expense description: "AIRBNB *HMQT5J6QQJ" expected: category_name: "Hotels" acceptable_alternatives: ["Travel"] # Streaming - US - id: cat_v2_med_023 difficulty: medium tags: [streaming, us] input: id: txn_v2_med_023 amount: 17.99 classification: expense description: "HULU LLC" expected: category_name: "Streaming Services" - id: cat_v2_med_024 difficulty: medium tags: [streaming, us] input: id: txn_v2_med_024 amount: 13.99 classification: expense description: "DISNEY PLUS" expected: category_name: "Streaming Services" # Income - US - id: cat_v2_med_025 difficulty: medium tags: [income, us, transfer] input: id: txn_v2_med_025 amount: 500.00 classification: income description: "VENMO CASHOUT" expected: category_name: "Income" # ============================================================================= # MEDIUM SAMPLES - European Merchants (15 samples) # ============================================================================= # Restaurants - Europe - id: cat_v2_med_eu_001 difficulty: medium tags: [restaurants, europe, uk] input: id: txn_v2_med_eu_001 amount: 78.50 classification: expense description: "WAGAMAMA LTD LONDON" expected: category_name: "Restaurants" - id: cat_v2_med_eu_002 difficulty: medium tags: [restaurants, europe, italy] input: id: txn_v2_med_eu_002 amount: 95.00 classification: expense description: "RISTORANTE MILANO SRL" expected: category_name: "Restaurants" - id: cat_v2_med_eu_003 difficulty: medium tags: [restaurants, europe, spain] input: id: txn_v2_med_eu_003 amount: 67.00 classification: expense description: "TELEPIZZA SAU MADRID" expected: category_name: "Food & Drink" acceptable_alternatives: ["Restaurants"] # Utilities - Europe - id: cat_v2_med_eu_004 difficulty: medium tags: [utilities, europe, uk] input: id: txn_v2_med_eu_004 amount: 156.00 classification: expense description: "BRITISH GAS SERVICES" expected: category_name: "Utilities" - id: cat_v2_med_eu_005 difficulty: medium tags: [utilities, europe, germany] input: id: txn_v2_med_eu_005 amount: 89.00 classification: expense description: "VODAFONE GMBH" expected: category_name: "Utilities" acceptable_alternatives: ["Subscriptions"] - id: cat_v2_med_eu_006 difficulty: medium tags: [utilities, europe, france] input: id: txn_v2_med_eu_006 amount: 112.00 classification: expense description: "EDF ENERGIE FRANCE" expected: category_name: "Utilities" # Public Transit - Europe - id: cat_v2_med_eu_007 difficulty: medium tags: [public_transit, europe, uk] input: id: txn_v2_med_eu_007 amount: 156.50 classification: expense description: "TFL TRAVEL LONDON" expected: category_name: "Public Transit" acceptable_alternatives: ["Transportation"] - id: cat_v2_med_eu_008 difficulty: medium tags: [public_transit, europe, germany] input: id: txn_v2_med_eu_008 amount: 89.00 classification: expense description: "DEUTSCHE BAHN AG" expected: category_name: "Public Transit" acceptable_alternatives: ["Transportation", "Travel"] - id: cat_v2_med_eu_009 difficulty: medium tags: [public_transit, europe, france] input: id: txn_v2_med_eu_009 amount: 75.00 classification: expense description: "SNCF VOYAGES" expected: category_name: "Public Transit" acceptable_alternatives: ["Transportation", "Travel"] # Entertainment - Europe - id: cat_v2_med_eu_010 difficulty: medium tags: [entertainment, europe, uk] input: id: txn_v2_med_eu_010 amount: 24.00 classification: expense description: "ODEON CINEMAS LTD" expected: category_name: "Entertainment" - id: cat_v2_med_eu_011 difficulty: medium tags: [entertainment, europe, uk] input: id: txn_v2_med_eu_011 amount: 145.00 classification: expense description: "TICKETMASTER UK LTD" expected: category_name: "Entertainment" # Gym - Europe - id: cat_v2_med_eu_012 difficulty: medium tags: [gym, europe, uk] input: id: txn_v2_med_eu_012 amount: 35.00 classification: expense description: "PUREGYM LTD" expected: category_name: "Gym & Fitness" acceptable_alternatives: ["Health & Wellness"] - id: cat_v2_med_eu_013 difficulty: medium tags: [gym, europe, germany] input: id: txn_v2_med_eu_013 amount: 29.99 classification: expense description: "MCFIT GMBH BERLIN" expected: category_name: "Gym & Fitness" acceptable_alternatives: ["Health & Wellness"] # Income - Europe - id: cat_v2_med_eu_014 difficulty: medium tags: [income, salary, europe, uk] input: id: txn_v2_med_eu_014 amount: 2850.00 classification: income description: "ACME LTD SALARY" expected: category_name: "Salary" - id: cat_v2_med_eu_015 difficulty: medium tags: [income, salary, europe, germany] input: id: txn_v2_med_eu_015 amount: 3200.00 classification: income description: "GEHALT FIRMA GMBH" expected: category_name: "Salary" # ============================================================================= # HARD SAMPLES - US Merchants (15 samples) # ============================================================================= # Big-box stores - id: cat_v2_hard_001 difficulty: hard tags: [ambiguous, us, multi_purpose_retailer] input: id: txn_v2_hard_001 amount: 156.78 classification: expense description: "TARGET #1234" expected: category_name: "Shopping" acceptable_alternatives: ["Groceries"] - id: cat_v2_hard_002 difficulty: hard tags: [ambiguous, us, multi_purpose_retailer] input: id: txn_v2_hard_002 amount: 234.56 classification: expense description: "WALMART SUPERCENTER" expected: category_name: "Shopping" acceptable_alternatives: ["Groceries"] # Online marketplaces - id: cat_v2_hard_003 difficulty: hard tags: [ambiguous, us, online_marketplace] input: id: txn_v2_hard_003 amount: 89.99 classification: expense description: "AMAZON.COM*1A2B3C4D" expected: category_name: "Shopping" # Square payments - id: cat_v2_hard_004 difficulty: hard tags: [ambiguous, us, square_payment] input: id: txn_v2_hard_004 amount: 45.00 classification: expense description: "SQ *DOWNTOWN CAFE" expected: category_name: "Coffee Shops" acceptable_alternatives: ["Restaurants"] # PayPal - id: cat_v2_hard_005 difficulty: hard tags: [ambiguous, us, payment_processor] input: id: txn_v2_hard_005 amount: 78.00 classification: expense description: "PAYPAL *JOHNSMITH" expected: category_name: null # Fast-casual - id: cat_v2_hard_006 difficulty: hard tags: [ambiguous, us, fast_casual] input: id: txn_v2_hard_006 amount: 34.50 classification: expense description: "PANERA BREAD #567" expected: category_name: "Restaurants" acceptable_alternatives: ["Food & Drink"] # Delivery services - id: cat_v2_hard_007 difficulty: hard tags: [ambiguous, us, delivery_service] input: id: txn_v2_hard_007 amount: 45.00 classification: expense description: "DOORDASH*CHIPOTLE" expected: category_name: "Food & Drink" acceptable_alternatives: ["Restaurants", "Food & Drink"] - id: cat_v2_hard_008 difficulty: hard tags: [ambiguous, us, delivery_service] input: id: txn_v2_hard_008 amount: 67.00 classification: expense description: "GRUBHUB*THAI KITCHEN" expected: category_name: "Restaurants" acceptable_alternatives: ["Food & Drink"] - id: cat_v2_hard_009 difficulty: hard tags: [ambiguous, us, delivery_service] input: id: txn_v2_hard_009 amount: 234.00 classification: expense description: "INSTACART*SAFEWAY" expected: category_name: "Groceries" # Amazon Prime - id: cat_v2_hard_010 difficulty: hard tags: [ambiguous, us, amazon] input: id: txn_v2_hard_010 amount: 14.99 classification: expense description: "AMAZON PRIME*1A2B3C" expected: category_name: "Subscriptions" # Convenience store - id: cat_v2_hard_011 difficulty: hard tags: [ambiguous, us, convenience_store] input: id: txn_v2_hard_011 amount: 12.50 classification: expense description: "7-ELEVEN #34567" expected: category_name: "Groceries" acceptable_alternatives: ["Food & Drink"] # Premium gym - id: cat_v2_hard_012 difficulty: hard tags: [ambiguous, us, premium_gym] input: id: txn_v2_hard_012 amount: 250.00 classification: expense description: "EQUINOX MEMBERSHIP" expected: category_name: "Gym & Fitness" # Streaming vs Subscription - id: cat_v2_hard_013 difficulty: hard tags: [ambiguous, us, streaming_subscription] input: id: txn_v2_hard_013 amount: 15.99 classification: expense description: "HBO MAX" expected: category_name: "Streaming Services" acceptable_alternatives: ["Subscriptions"] # Etsy - id: cat_v2_hard_014 difficulty: hard tags: [ambiguous, us, online_marketplace] input: id: txn_v2_hard_014 amount: 45.00 classification: expense description: "ETSY.COM" expected: category_name: "Shopping" # IKEA - id: cat_v2_hard_015 difficulty: hard tags: [ambiguous, us, home_goods] input: id: txn_v2_hard_015 amount: 423.00 classification: expense description: "IKEA US EAST LLC" expected: category_name: "Shopping" # ============================================================================= # HARD SAMPLES - European Merchants (10 samples) # ============================================================================= # Multi-purpose retailers - Europe - id: cat_v2_hard_eu_001 difficulty: hard tags: [ambiguous, europe, uk, multi_purpose_retailer] input: id: txn_v2_hard_eu_001 amount: 156.00 classification: expense description: "MARKS & SPENCER PLC" expected: category_name: "Shopping" acceptable_alternatives: ["Groceries", "Clothing"] - id: cat_v2_hard_eu_002 difficulty: hard tags: [ambiguous, europe, uk, multi_purpose_retailer] input: id: txn_v2_hard_eu_002 amount: 89.50 classification: expense description: "ASDA STORES LTD" expected: category_name: "Groceries" acceptable_alternatives: ["Shopping"] - id: cat_v2_hard_eu_003 difficulty: hard tags: [ambiguous, europe, france, multi_purpose_retailer] input: id: txn_v2_hard_eu_003 amount: 234.00 classification: expense description: "AUCHAN HYPERMARCHE" expected: category_name: "Groceries" acceptable_alternatives: ["Shopping"] # Delivery - Europe - id: cat_v2_hard_eu_004 difficulty: hard tags: [ambiguous, europe, uk, delivery_service] input: id: txn_v2_hard_eu_004 amount: 32.50 classification: expense description: "DELIVEROO UK LTD" expected: category_name: "Restaurants" acceptable_alternatives: ["Food & Drink"] - id: cat_v2_hard_eu_005 difficulty: hard tags: [ambiguous, europe, germany, delivery_service] input: id: txn_v2_hard_eu_005 amount: 28.90 classification: expense description: "LIEFERANDO GMBH" expected: category_name: "Restaurants" acceptable_alternatives: ["Food & Drink"] # Online marketplaces - Europe - id: cat_v2_hard_eu_006 difficulty: hard tags: [ambiguous, europe, online_marketplace] input: id: txn_v2_hard_eu_006 amount: 67.00 classification: expense description: "AMAZON.CO.UK" expected: category_name: "Shopping" - id: cat_v2_hard_eu_007 difficulty: hard tags: [ambiguous, europe, germany, online_marketplace] input: id: txn_v2_hard_eu_007 amount: 123.00 classification: expense description: "ZALANDO SE" expected: category_name: "Clothing" acceptable_alternatives: ["Shopping"] # Payment processors - Europe - id: cat_v2_hard_eu_008 difficulty: hard tags: [ambiguous, europe, payment_processor] input: id: txn_v2_hard_eu_008 amount: 45.00 classification: expense description: "PAYPAL EUROPE" expected: category_name: null - id: cat_v2_hard_eu_009 difficulty: hard tags: [ambiguous, europe, uk, payment_processor] input: id: txn_v2_hard_eu_009 amount: 89.00 classification: expense description: "KLARNA UK LTD" expected: category_name: null # Pharmacy/Drugstore - Europe - id: cat_v2_hard_eu_010 difficulty: hard tags: [ambiguous, europe, uk, drugstore] input: id: txn_v2_hard_eu_010 amount: 34.50 classification: expense description: "BOOTS UK LTD" expected: category_name: "Pharmacy" acceptable_alternatives: ["Personal Care", "Health & Wellness"] # ============================================================================= # EDGE CASES - Should return null (15 samples) # ============================================================================= # Generic POS transactions - id: cat_v2_edge_001 difficulty: edge_case tags: [should_be_null, generic_pos] input: id: txn_v2_edge_001 amount: 15.00 classification: expense description: "POS DEBIT 12345" expected: category_name: null - id: cat_v2_edge_002 difficulty: edge_case tags: [should_be_null, generic_pos] input: id: txn_v2_edge_002 amount: 50.00 classification: expense description: "DEBIT CARD PURCHASE" expected: category_name: null - id: cat_v2_edge_003 difficulty: edge_case tags: [should_be_null, generic_pos, europe] input: id: txn_v2_edge_003 amount: 45.00 classification: expense description: "CARTE BANCAIRE" expected: category_name: null # ACH/Wire transfers - id: cat_v2_edge_004 difficulty: edge_case tags: [should_be_null, transfer] input: id: txn_v2_edge_004 amount: 100.00 classification: expense description: "ACH WITHDRAWAL" expected: category_name: null - id: cat_v2_edge_005 difficulty: edge_case tags: [should_be_null, transfer] input: id: txn_v2_edge_005 amount: 500.00 classification: expense description: "ONLINE TRANSFER TO CHK 1234" expected: category_name: null - id: cat_v2_edge_006 difficulty: edge_case tags: [should_be_null, transfer, europe] input: id: txn_v2_edge_006 amount: 250.00 classification: expense description: "SEPA TRANSFER" expected: category_name: null - id: cat_v2_edge_007 difficulty: edge_case tags: [should_be_null, transfer] input: id: txn_v2_edge_007 amount: 1500.00 classification: expense description: "WIRE TRANSFER OUT" expected: category_name: null # ATM - id: cat_v2_edge_008 difficulty: edge_case tags: [should_be_null, atm] input: id: txn_v2_edge_008 amount: 200.00 classification: expense description: "ATM WITHDRAWAL 12345" expected: category_name: null - id: cat_v2_edge_009 difficulty: edge_case tags: [should_be_null, atm, europe] input: id: txn_v2_edge_009 amount: 150.00 classification: expense description: "GELDAUTOMAT ABHEBUNG" expected: category_name: null # Unknown/generic business names - id: cat_v2_edge_010 difficulty: edge_case tags: [should_be_null, unknown_merchant] input: id: txn_v2_edge_010 amount: 75.00 classification: expense description: "MISC SERVICES LLC" expected: category_name: null # Reference numbers only - id: cat_v2_edge_011 difficulty: edge_case tags: [should_be_null, reference_only] input: id: txn_v2_edge_011 amount: 234.56 classification: expense description: "REF #789456123" expected: category_name: null # Checks - id: cat_v2_edge_012 difficulty: edge_case tags: [should_be_null, check] input: id: txn_v2_edge_012 amount: 350.00 classification: expense description: "CHECK #1234" expected: category_name: null # Bank fees - id: cat_v2_edge_013 difficulty: edge_case tags: [should_be_null, fee] input: id: txn_v2_edge_013 amount: 35.00 classification: expense description: "SERVICE CHARGE" expected: category_name: null # Cryptic abbreviations - id: cat_v2_edge_014 difficulty: edge_case tags: [should_be_null, cryptic] input: id: txn_v2_edge_014 amount: 45.67 classification: expense description: "TXN*89234*AUTH" expected: category_name: null - id: cat_v2_edge_015 difficulty: edge_case tags: [should_be_null, cryptic] input: id: txn_v2_edge_015 amount: 123.45 classification: expense description: "PURCHASE 847392" expected: category_name: null # ============================================================================= # ADDITIONAL SAMPLES - Mixed regions and categories (19 samples to reach 150) # ============================================================================= # Additional US Easy samples - id: cat_v2_add_001 difficulty: easy tags: [food_and_drink, us] input: id: txn_v2_add_001 amount: 11.50 classification: expense description: "CHICK-FIL-A #1234" expected: category_name: "Food & Drink" acceptable_alternatives: ["Restaurants"] - id: cat_v2_add_002 difficulty: easy tags: [food_and_drink, us] input: id: txn_v2_add_002 amount: 7.99 classification: expense description: "POPEYES #5678" expected: category_name: "Food & Drink" acceptable_alternatives: ["Restaurants"] - id: cat_v2_add_003 difficulty: easy tags: [groceries, us] input: id: txn_v2_add_003 amount: 134.50 classification: expense description: "SAFEWAY #1234" expected: category_name: "Groceries" - id: cat_v2_add_004 difficulty: easy tags: [gas, us] input: id: txn_v2_add_004 amount: 55.00 classification: expense description: "COSTCO GAS #789" expected: category_name: "Gas & Fuel" # Additional European Easy samples - id: cat_v2_add_005 difficulty: easy tags: [groceries, europe, spain] input: id: txn_v2_add_005 amount: 89.00 classification: expense description: "MERCADONA SA" expected: category_name: "Groceries" acceptable_alternatives: ["Food & Drink"] - id: cat_v2_add_006 difficulty: easy tags: [groceries, europe, italy] input: id: txn_v2_add_006 amount: 67.50 classification: expense description: "ESSELUNGA SPA MILANO" expected: category_name: "Groceries" acceptable_alternatives: ["Food & Drink"] - id: cat_v2_add_007 difficulty: easy tags: [flights, europe, spain] input: id: txn_v2_add_007 amount: 156.00 classification: expense description: "VUELING AIRLINES SA" expected: category_name: "Flights" acceptable_alternatives: ["Travel"] - id: cat_v2_add_008 difficulty: easy tags: [flights, europe, netherlands] input: id: txn_v2_add_008 amount: 234.00 classification: expense description: "KLM ROYAL DUTCH" expected: category_name: "Flights" acceptable_alternatives: ["Travel"] # Additional Medium samples - id: cat_v2_add_009 difficulty: medium tags: [restaurants, us] input: id: txn_v2_add_009 amount: 56.00 classification: expense description: "APPLEBEES #789" expected: category_name: "Restaurants" - id: cat_v2_add_010 difficulty: medium tags: [restaurants, us] input: id: txn_v2_add_010 amount: 78.50 classification: expense description: "RED LOBSTER #456" expected: category_name: "Restaurants" - id: cat_v2_add_011 difficulty: medium tags: [subscriptions, us] input: id: txn_v2_add_011 amount: 14.99 classification: expense description: "MICROSOFT *OFFICE365" expected: category_name: "Subscriptions" - id: cat_v2_add_012 difficulty: medium tags: [subscriptions, us] input: id: txn_v2_add_012 amount: 11.99 classification: expense description: "ADOBE CREATIVE CLOUD" expected: category_name: "Subscriptions" - id: cat_v2_add_013 difficulty: medium tags: [personal_care, europe, uk] input: id: txn_v2_add_013 amount: 35.00 classification: expense description: "SUPERDRUG STORES" expected: category_name: "Personal Care" acceptable_alternatives: ["Pharmacy"] # Additional Hard samples - id: cat_v2_add_014 difficulty: hard tags: [ambiguous, us, delivery_service] input: id: txn_v2_add_014 amount: 156.00 classification: expense description: "INSTACART*COSTCO" expected: category_name: "Groceries" acceptable_alternatives: ["Shopping"] - id: cat_v2_add_015 difficulty: hard tags: [ambiguous, europe, spain, delivery_service] input: id: txn_v2_add_015 amount: 45.00 classification: expense description: "GLOVO APP BARCELONA" expected: category_name: "Restaurants" acceptable_alternatives: ["Groceries", "Food & Drink"] - id: cat_v2_add_016 difficulty: hard tags: [ambiguous, europe, poland, multi_purpose_retailer] input: id: txn_v2_add_016 amount: 178.00 classification: expense description: "BIEDRONKA SP ZOO" expected: category_name: "Groceries" # Additional Edge cases - id: cat_v2_add_017 difficulty: edge_case tags: [should_be_null, europe, generic] input: id: txn_v2_add_017 amount: 89.00 classification: expense description: "VIREMENT SEPA" expected: category_name: null - id: cat_v2_add_018 difficulty: edge_case tags: [should_be_null, generic] input: id: txn_v2_add_018 amount: 25.00 classification: expense description: "RECURRING PAYMENT" expected: category_name: null - id: cat_v2_add_019 difficulty: edge_case tags: [should_be_null, europe, uk, generic] input: id: txn_v2_add_019 amount: 15.00 classification: expense description: "DIRECT DEBIT PAYMENT" expected: category_name: null # ============================================================================= # CHALLENGING SAMPLES - Local businesses, abbreviations, ambiguous # ============================================================================= # Local/Unknown businesses - Hard to categorize without context - id: cat_v2_challenge_001 difficulty: hard tags: [local_business, ambiguous] input: id: txn_v2_ch_001 amount: 45.00 classification: expense description: "MIKE'S PLACE" expected: category_name: null - id: cat_v2_challenge_002 difficulty: hard tags: [local_business, ambiguous] input: id: txn_v2_ch_002 amount: 67.50 classification: expense description: "THE CORNER SPOT LLC" expected: category_name: null - id: cat_v2_challenge_003 difficulty: hard tags: [local_business, ambiguous] input: id: txn_v2_ch_003 amount: 23.99 classification: expense description: "MAIN ST MARKET" expected: category_name: "Groceries" acceptable_alternatives: ["Shopping"] - id: cat_v2_challenge_004 difficulty: hard tags: [local_business, ambiguous] input: id: txn_v2_ch_004 amount: 89.00 classification: expense description: "DOWNTOWN GRILL & BAR" expected: category_name: "Restaurants" - id: cat_v2_challenge_005 difficulty: hard tags: [local_business, ambiguous] input: id: txn_v2_ch_005 amount: 15.00 classification: expense description: "JAVA JOE'S" expected: category_name: "Coffee Shops" acceptable_alternatives: ["Restaurants"] # Abbreviated/truncated merchant names - id: cat_v2_challenge_006 difficulty: hard tags: [abbreviated, ambiguous] input: id: txn_v2_ch_006 amount: 34.50 classification: expense description: "AMZN MKTP US*2K9X7Y" expected: category_name: "Shopping" - id: cat_v2_challenge_007 difficulty: hard tags: [abbreviated, ambiguous] input: id: txn_v2_ch_007 amount: 12.99 classification: expense description: "WM SUPERCENTER #" expected: category_name: "Shopping" acceptable_alternatives: ["Groceries"] - id: cat_v2_challenge_008 difficulty: hard tags: [abbreviated, ambiguous] input: id: txn_v2_ch_008 amount: 8.50 classification: expense description: "SBUX 12345" expected: category_name: "Coffee Shops" - id: cat_v2_challenge_009 difficulty: hard tags: [abbreviated, ambiguous] input: id: txn_v2_ch_009 amount: 156.00 classification: expense description: "TGT*" expected: category_name: "Shopping" acceptable_alternatives: ["Groceries"] - id: cat_v2_challenge_010 difficulty: hard tags: [abbreviated, ambiguous] input: id: txn_v2_ch_010 amount: 45.00 classification: expense description: "SQ *JOE SMITH" expected: category_name: null # Multiple category signals - genuinely ambiguous - id: cat_v2_challenge_011 difficulty: hard tags: [multi_signal, ambiguous] input: id: txn_v2_ch_011 amount: 234.00 classification: expense description: "AMAZON FRESH" expected: category_name: "Groceries" - id: cat_v2_challenge_012 difficulty: hard tags: [multi_signal, ambiguous] input: id: txn_v2_ch_012 amount: 45.00 classification: expense description: "TARGET.COM" expected: category_name: "Shopping" acceptable_alternatives: ["Groceries"] - id: cat_v2_challenge_013 difficulty: hard tags: [multi_signal, ambiguous] input: id: txn_v2_ch_013 amount: 67.00 classification: expense description: "WALGREENS PHARMACY" expected: category_name: "Pharmacy" acceptable_alternatives: ["Health & Wellness", "Groceries"] - id: cat_v2_challenge_014 difficulty: hard tags: [multi_signal, ambiguous] input: id: txn_v2_ch_014 amount: 23.00 classification: expense description: "CVS STORE" expected: category_name: "Pharmacy" acceptable_alternatives: ["Health & Wellness", "Groceries"] # Numeric/cryptic descriptions - id: cat_v2_challenge_015 difficulty: edge_case tags: [cryptic, should_be_null] input: id: txn_v2_ch_015 amount: 78.00 classification: expense description: "12345678901234" expected: category_name: null - id: cat_v2_challenge_016 difficulty: edge_case tags: [cryptic, should_be_null] input: id: txn_v2_ch_016 amount: 150.00 classification: expense description: "PMT*AUTH*9876" expected: category_name: null - id: cat_v2_challenge_017 difficulty: edge_case tags: [cryptic, should_be_null] input: id: txn_v2_ch_017 amount: 99.00 classification: expense description: "CHECKCARD 0423" expected: category_name: null - id: cat_v2_challenge_018 difficulty: edge_case tags: [cryptic, should_be_null] input: id: txn_v2_ch_018 amount: 200.00 classification: expense description: "EXTERNAL WITHDRAWAL" expected: category_name: null # Similar names, different categories - id: cat_v2_challenge_019 difficulty: hard tags: [similar_names, ambiguous] input: id: txn_v2_ch_019 amount: 45.00 classification: expense description: "APPLE STORE R123" expected: category_name: "Electronics" acceptable_alternatives: ["Shopping"] - id: cat_v2_challenge_020 difficulty: hard tags: [similar_names, ambiguous] input: id: txn_v2_ch_020 amount: 2.99 classification: expense description: "APPLE.COM BILL" expected: category_name: "Subscriptions" - id: cat_v2_challenge_021 difficulty: hard tags: [similar_names, ambiguous] input: id: txn_v2_ch_021 amount: 0.99 classification: expense description: "GOOGLE PLAY" expected: category_name: "Subscriptions" acceptable_alternatives: ["Shopping"] - id: cat_v2_challenge_022 difficulty: hard tags: [similar_names, ambiguous] input: id: txn_v2_ch_022 amount: 1299.00 classification: expense description: "GOOGLE STORE" expected: category_name: "Electronics" acceptable_alternatives: ["Shopping"] # International formats - id: cat_v2_challenge_023 difficulty: hard tags: [international, europe] input: id: txn_v2_ch_023 amount: 45.00 classification: expense description: "REWE MARKT GMBH" expected: category_name: "Groceries" - id: cat_v2_challenge_024 difficulty: hard tags: [international, europe] input: id: txn_v2_ch_024 amount: 89.00 classification: expense description: "MEDIAMARKT SATURN" expected: category_name: "Electronics" acceptable_alternatives: ["Shopping"] - id: cat_v2_challenge_025 difficulty: hard tags: [international, europe] input: id: txn_v2_ch_025 amount: 34.00 classification: expense description: "PRIMARK STORES LTD" expected: category_name: "Clothing" acceptable_alternatives: ["Shopping"] - id: cat_v2_challenge_026 difficulty: hard tags: [international, asia] input: id: txn_v2_ch_026 amount: 78.00 classification: expense description: "UNIQLO CO LTD" expected: category_name: "Clothing" acceptable_alternatives: ["Shopping"] # Delivery with ambiguous underlying merchant - id: cat_v2_challenge_027 difficulty: hard tags: [delivery, ambiguous] input: id: txn_v2_ch_027 amount: 45.00 classification: expense description: "DOORDASH*" expected: category_name: "Restaurants" acceptable_alternatives: ["Food & Drink"] - id: cat_v2_challenge_028 difficulty: hard tags: [delivery, ambiguous] input: id: txn_v2_ch_028 amount: 89.00 classification: expense description: "UBER EATS" expected: category_name: "Restaurants" acceptable_alternatives: ["Food & Drink"] - id: cat_v2_challenge_029 difficulty: hard tags: [delivery, ambiguous] input: id: txn_v2_ch_029 amount: 123.00 classification: expense description: "INSTACART" expected: category_name: "Groceries" # Gym/Fitness edge cases - id: cat_v2_challenge_030 difficulty: hard tags: [gym, ambiguous] input: id: txn_v2_ch_030 amount: 15.00 classification: expense description: "CLASSPASS INC" expected: category_name: "Gym & Fitness" acceptable_alternatives: ["Health & Wellness", "Subscriptions"] # Streaming vs Subscription edge cases - id: cat_v2_challenge_031 difficulty: hard tags: [streaming, subscription, ambiguous] input: id: txn_v2_ch_031 amount: 6.99 classification: expense description: "AMAZON VIDEO" expected: category_name: "Streaming Services" acceptable_alternatives: ["Subscriptions"] - id: cat_v2_challenge_032 difficulty: hard tags: [streaming, subscription, ambiguous] input: id: txn_v2_ch_032 amount: 9.99 classification: expense description: "YOUTUBE PREMIUM" expected: category_name: "Streaming Services" acceptable_alternatives: ["Subscriptions"] - id: cat_v2_challenge_033 difficulty: hard tags: [streaming, subscription, ambiguous] input: id: txn_v2_ch_033 amount: 14.99 classification: expense description: "APPLE TV+" expected: category_name: "Streaming Services" acceptable_alternatives: ["Subscriptions"] # P2P and transfer ambiguity - id: cat_v2_challenge_034 difficulty: edge_case tags: [p2p, should_be_null] input: id: txn_v2_ch_034 amount: 50.00 classification: expense description: "VENMO *JOHN DOE" expected: category_name: null - id: cat_v2_challenge_035 difficulty: edge_case tags: [p2p, should_be_null] input: id: txn_v2_ch_035 amount: 100.00 classification: expense description: "ZELLE PAYMENT TO" expected: category_name: null - id: cat_v2_challenge_036 difficulty: medium tags: [p2p, income] input: id: txn_v2_ch_036 amount: 200.00 classification: income description: "VENMO *PAYMENT FROM" expected: category_name: "Income" # Food-related ambiguity - id: cat_v2_challenge_037 difficulty: hard tags: [food, ambiguous] input: id: txn_v2_ch_037 amount: 12.00 classification: expense description: "FIVE GUYS #1234" expected: category_name: "Food & Drink" acceptable_alternatives: ["Restaurants"] - id: cat_v2_challenge_038 difficulty: hard tags: [food, ambiguous] input: id: txn_v2_ch_038 amount: 45.00 classification: expense description: "SHAKE SHACK" expected: category_name: "Food & Drink" acceptable_alternatives: ["Restaurants"] - id: cat_v2_challenge_039 difficulty: hard tags: [food, ambiguous] input: id: txn_v2_ch_039 amount: 8.00 classification: expense description: "SWEETGREEN" expected: category_name: "Restaurants" acceptable_alternatives: ["Food & Drink"] - id: cat_v2_challenge_040 difficulty: hard tags: [food, ambiguous] input: id: txn_v2_ch_040 amount: 23.00 classification: expense description: "CAVA GRILL" expected: category_name: "Restaurants" acceptable_alternatives: ["Food & Drink"] # Hotel/Travel edge cases - id: cat_v2_challenge_041 difficulty: hard tags: [travel, ambiguous] input: id: txn_v2_ch_041 amount: 89.00 classification: expense description: "BOOKING.COM" expected: category_name: "Hotels" acceptable_alternatives: ["Travel"] - id: cat_v2_challenge_042 difficulty: hard tags: [travel, ambiguous] input: id: txn_v2_ch_042 amount: 156.00 classification: expense description: "EXPEDIA INC" expected: category_name: "Travel" acceptable_alternatives: ["Hotels", "Flights"] - id: cat_v2_challenge_043 difficulty: hard tags: [travel, ambiguous] input: id: txn_v2_ch_043 amount: 234.00 classification: expense description: "VRBO.COM" expected: category_name: "Hotels" acceptable_alternatives: ["Travel"] # Gas station convenience purchases - id: cat_v2_challenge_044 difficulty: hard tags: [gas, convenience, ambiguous] input: id: txn_v2_ch_044 amount: 8.50 classification: expense description: "SHELL SERVICE STATION" expected: category_name: "Gas & Fuel" acceptable_alternatives: ["Groceries"] - id: cat_v2_challenge_045 difficulty: hard tags: [gas, convenience, ambiguous] input: id: txn_v2_ch_045 amount: 12.00 classification: expense description: "SPEEDWAY" expected: category_name: "Gas & Fuel" acceptable_alternatives: ["Groceries"] # Income edge cases - id: cat_v2_challenge_046 difficulty: medium tags: [income, ambiguous] input: id: txn_v2_ch_046 amount: 1500.00 classification: income description: "ACH CREDIT" expected: category_name: "Income" acceptable_alternatives: ["Salary"] - id: cat_v2_challenge_047 difficulty: medium tags: [income, ambiguous] input: id: txn_v2_ch_047 amount: 500.00 classification: income description: "INTEREST PAYMENT" expected: category_name: "Income" - id: cat_v2_challenge_048 difficulty: medium tags: [income, ambiguous] input: id: txn_v2_ch_048 amount: 234.00 classification: income description: "DIVIDEND" expected: category_name: "Income" # Cryptic European formats - id: cat_v2_challenge_049 difficulty: edge_case tags: [europe, cryptic, should_be_null] input: id: txn_v2_ch_049 amount: 45.00 classification: expense description: "LASTSCHRIFT" expected: category_name: null - id: cat_v2_challenge_050 difficulty: edge_case tags: [europe, cryptic, should_be_null] input: id: txn_v2_ch_050 amount: 89.00 classification: expense description: "PRELEVEMENT" expected: category_name: null