Synthetic dataset of payment transactions processed by a payment processor. Each row represents one transaction.
", "source": { "parquet": "data/payments.parquet" }, "columns": [ { "name": "psp_reference", "description": "Unique payment identifier.
", "type": "number(id)", "constraints": [ "primary_key", "unique", "required" ], "examples": [ 10000636248, 29933254267, 49981130818, 70032289018, 89998294921 ] }, { "name": "merchant", "description": "Merchant name.
", "type": "enum", "constraints": [ "required" ], "values": [ "Belles_cookbook_store", "Crossfit_Hanna", "Golfclub_Baron_Friso", "Martinis_Fine_Steakhouse", "Rafa_AI" ] }, { "name": "card_scheme", "description": "Card scheme (network) used for the transaction.
", "type": "enum", "constraints": [ "required" ], "values": [ "GlobalCard", "NexPay", "SwiftCharge", "TransactPlus" ] }, { "name": "year", "description": "Year of payment initiation. Always 2023 in this dataset.
", "type": "number(ordinal)", "constraints": [ "required" ], "range": { "min": 2023, "max": 2023 } }, { "name": "hour_of_day", "description": "Hour of the day of payment initiation (0-23).
", "type": "number(ordinal)", "constraints": [ "required" ], "range": { "min": 0, "max": 23 } }, { "name": "minute_of_hour", "description": "Minute of the hour of payment initiation (0-59).
", "type": "number(ordinal)", "constraints": [ "required" ], "range": { "min": 0, "max": 59 } }, { "name": "day_of_year", "description": "Day of the year of payment initiation (1-365).
", "type": "number(ordinal)", "constraints": [ "required" ], "range": { "min": 1, "max": 365 } }, { "name": "month", "description": "Month of payment initiation (1-12).
", "type": "number(ordinal)", "constraints": [ "required" ], "range": { "min": 1, "max": 12 } }, { "name": "is_credit", "description": "Whether the card used is a credit card. FALSE indicates a debit card. Credit transactions are typically more expensive.
", "type": "boolean", "constraints": [ "required" ] }, { "name": "eur_amount", "description": "Payment amount in euros.
", "type": "number(quantity)", "units": "EUR", "constraints": [ "required" ], "range": { "min": 0.5, "max": 4811.76 } }, { "name": "ip_country", "description": "Country the shopper was in at the time of the transaction, determined by IP address. ISO 3166-1 alpha-2 code.
", "type": "enum", "constraints": [ "required" ], "values": [ "BE", "ES", "FR", "GR", "IT", "LU", "NL", "SE" ] }, { "name": "issuing_country", "description": "Country of the card-issuing bank. ISO 3166-1 alpha-2 code. When this matches acquirer_country, the transaction is domestic (intracountry).
", "type": "enum", "constraints": [ "required" ], "values": [ "BE", "ES", "FR", "GR", "IT", "LU", "NL", "SE" ] }, { "name": "device_type", "description": "Device type used for the transaction.
", "type": "enum", "constraints": [ "required" ], "values": [ "Android", "iOS", "Linux", "MacOS", "Other", "Windows" ] }, { "name": "ip_address", "description": "Hashed shopper IP address.
", "type": "string", "constraints": [ "required" ], "examples": [ "__-7u3f9uJKdXS3u_2ukdQ", "bYuXXkz9nZuRjS0r9dT-_w", "jyxXoQ7r78mNUH0BnlngEw", "s-xemKxVf5o0K46vaODxhA", "ZzZYJhXWE4MTCE9vcHnCdQ" ] }, { "name": "email_address", "description": "Hashed shopper email address. May be empty.
", "type": "string", "examples": [ "__-8prajRhB4WeqqIoY5PA", "Byq-k5LkiiVbiYjHS95XsQ", "jvXaD_MZf_Ljdf7UvAUMpQ", "Rz-JZg73tHtXbVEj0wkr_g", "ZZzHkjMLX3_pzQtc1HmvBg" ] }, { "name": "card_number", "description": "Hashed card number.
", "type": "string", "constraints": [ "required" ], "examples": [ "__8Fy8ayxoTnl0EX9DtIhw", "c8fAIVb46qwMwy1_z2TpxA", "k97dMMQVxeLQjnWvk0hy3Q", "s24En6cJp3dNBoLHXSWiWg", "zzzp-SYj0U6e5r2ioWVniQ" ] }, { "name": "shopper_interaction", "description": "Payment method.
", "type": "enum", "constraints": [ "required" ], "values": [ "Ecommerce", "POS" ], "value_labels": { "Ecommerce": "Online transactions", "POS": "In-person or in-store transactions" } }, { "name": "card_bin", "description": "Bank Identification Number (first digits of card number).
", "type": "number(id)", "constraints": [ "required" ], "examples": [ 4017, 4526, 4571, 4802, 4920 ] }, { "name": "has_fraudulent_dispute", "description": "Whether the issuing bank flagged the transaction as a fraudulent dispute.
", "type": "boolean", "constraints": [ "required" ] }, { "name": "is_refused_by_adyen", "description": "Whether the transaction was refused by Adyen.
", "type": "boolean", "constraints": [ "required" ] }, { "name": "aci", "description": "Authorization Characteristics Indicator. Identifies how the transaction was submitted to the acquirer.
", "type": "enum", "constraints": [ "required" ], "values": [ "A", "B", "C", "D", "E", "F", "G" ], "value_labels": { "A": "Card present, non-authenticated", "B": "Card present, authenticated", "C": "Tokenized with mobile device", "D": "Card not present, card on file", "E": "Card not present, recurring", "F": "Card not present, 3-D Secure", "G": "Card not present, non-3-D Secure" } }, { "name": "acquirer_country", "description": "Country of the acquiring bank. ISO 3166-1 alpha-2 code.
", "type": "enum", "constraints": [ "required" ], "values": [ "FR", "GB", "IT", "NL", "US" ] } ] }, { "name": "acquirer_countries", "description": "Lookup table mapping acquirer names to their country codes.
", "source": { "parquet": "data/acquirer_countries.parquet" }, "columns": [ { "name": "acquirer", "description": "Name of the acquiring bank.
", "type": "string", "constraints": [ "primary_key", "unique", "required" ], "referenced_by": [ { "table": "merchant_acquirers", "column": "acquirer" } ], "examples": [ "bank_of_springfield", "dagoberts_vault", "gringotts", "medici", "the_savings_and_loan_bank" ] }, { "name": "country_code", "description": "Country of the acquirer. ISO 3166-1 alpha-2 code.
", "type": "enum", "constraints": [ "required" ], "values": [ "FR", "GB", "IT", "NL", "US" ] } ] }, { "name": "merchants", "description": "Merchant profiles with business classification and processing configuration. Each row represents one merchant.
", "source": { "parquet": "data/merchants.parquet" }, "columns": [ { "name": "merchant", "description": "Merchant name.
", "type": "string", "constraints": [ "primary_key", "unique", "required" ], "referenced_by": [ { "table": "merchant_acquirers", "column": "merchant" }, { "table": "merchant_months", "column": "merchant" } ], "examples": [ "AI_Pro_Labs", "Crafty_Cuisine", "Gym_Pro", "Read_and_Co", "Yoga_Masters" ] }, { "name": "capture_delay", "description": "Capture delay range. Faster capture is generally more expensive.
", "type": "enum", "constraints": [ "required" ], "values": [ "immediate", "<3", "3-5", ">5", "manual" ], "value_labels": { "3-5": "3 to 5 days", "<3": "Under 3 days", ">5": "Over 5 days", "immediate": "Immediate capture", "manual": "Manual capture" } }, { "name": "merchant_category_code", "description": "Four-digit Merchant Category Code classifying the business type.
", "type": "number(id)", "constraints": [ "foreign_key", "required" ], "references": { "table": "merchant_category_codes", "column": "mcc" }, "examples": [ 5812, 5814, 7372, 7997, 8299 ] }, { "name": "account_type", "description": "Business model classification.
", "type": "enum", "constraints": [ "required" ], "values": [ "D", "F", "H", "R", "S" ], "value_labels": { "D": "Enterprise - Digital", "F": "Platform - Franchise", "H": "Enterprise - Hospitality", "R": "Enterprise - Retail", "S": "Platform - SaaS" } } ] }, { "name": "merchant_acquirers", "description": "Junction table linking merchants to their acquiring banks. A merchant may route transactions through multiple acquirers (typically in different countries) to enable local acquiring.
", "source": { "parquet": "data/merchant_acquirers.parquet" }, "columns": [ { "name": "merchant", "description": "Merchant name.
", "type": "string", "constraints": [ "foreign_key", "required" ], "references": { "table": "merchants", "column": "merchant" }, "examples": [ "AI_Pro_Labs", "Crafty_Cuisine", "Gym_Pro", "Read_and_Co", "Yoga_Masters" ] }, { "name": "acquirer", "description": "Name of the acquiring bank.
", "type": "string", "constraints": [ "foreign_key", "required" ], "references": { "table": "acquirer_countries", "column": "acquirer" }, "examples": [ "bank_of_springfield", "dagoberts_vault", "gringotts", "medici", "the_savings_and_loan_bank" ] } ] }, { "name": "fees", "description": "Fee rules for payment processing. Each row is a rule with constraints that determine which transactions it applies to. A rule matches a transaction when all non-null fields match. Null (scalar) or empty (list) means \"matches all values.\" The fee for a matched transaction is: fixed_amount + rate * eur_amount / 10000.
", "source": { "parquet": "data/fees.parquet" }, "columns": [ { "name": "ID", "description": "Unique identifier for the fee rule.
", "type": "number(id)", "constraints": [ "primary_key", "unique", "required" ], "examples": [ 1, 251, 500, 750, 1000 ] }, { "name": "card_scheme", "description": "Card scheme this rule applies to. Always set (never null).
", "type": "enum", "constraints": [ "required" ], "values": [ "GlobalCard", "NexPay", "SwiftCharge", "TransactPlus" ] }, { "name": "capture_delay", "description": "Capture delay range this rule applies to. Null means all. Matches the same enum used in the merchants table.
", "type": "enum", "values": [ "immediate", "<3", "3-5", ">5", "manual" ], "value_labels": { "3-5": "3 to 5 days", "<3": "Under 3 days", ">5": "Over 5 days", "immediate": "Immediate capture", "manual": "Manual capture" } }, { "name": "fraud_percent_min", "description": "Minimum monthly fraud level (%) this rule applies to (inclusive). -Inf means no lower bound, and is by far the most common value (926 of 1000 rules); the finite values observed run from 7.2 to 8.3.
Maximum monthly fraud level (%) this rule applies to (exclusive). Inf means no upper bound, and is by far the most common value (921 of 1000 rules); the finite values observed run from 7.2 to 8.3.
Monthly transaction volume range this rule applies to. Null means all.
", "type": "enum", "values": [ "<100k", "100k-1m", "1m-5m", ">5m" ], "value_labels": { "100k-1m": "100k to 1m euros", "1m-5m": "1m to 5m euros", "<100k": "Under 100k euros", ">5m": "Over 5m euros" } }, { "name": "is_credit", "description": "Whether this rule applies to credit (TRUE) or debit (FALSE) transactions. Null means both.
", "type": "boolean" }, { "name": "fixed_amount", "description": "Fixed fee component (also called \"absolute fee\") in euros per transaction.
", "type": "number(quantity)", "units": "EUR", "constraints": [ "required" ], "range": { "min": 0, "max": 0.14 } }, { "name": "rate", "description": "Variable fee rate (also called \"relative fee\"). Multiply by transaction value and divide by 10000 to get the variable component in euros.
", "type": "number(quantity)", "constraints": [ "required" ], "range": { "min": 10, "max": 99 } }, { "name": "intracountry", "description": "Whether this rule applies to domestic (TRUE) or international (FALSE) transactions. A transaction is domestic when issuing_country equals acquirer_country. Null means both.
", "type": "boolean" } ] }, { "name": "merchant_months", "description": "Monthly aggregates per merchant, computed from the payments data. Used for matching payments to fee rules based on monthly fraud level and transaction volume thresholds.
", "source": { "parquet": "data/merchant_months.parquet" }, "columns": [ { "name": "merchant", "description": "Merchant name.
", "type": "string", "constraints": [ "primary_key", "foreign_key", "unique", "required" ], "references": { "table": "merchants", "column": "merchant" }, "examples": [ "Belles_cookbook_store", "Crossfit_Hanna", "Golfclub_Baron_Friso", "Martinis_Fine_Steakhouse", "Rafa_AI" ] }, { "name": "year", "description": "Year.
", "type": "number(ordinal)", "constraints": [ "primary_key", "unique", "required" ], "range": { "min": 2023, "max": 2023 } }, { "name": "month", "description": "Month (1-12).
", "type": "number(ordinal)", "constraints": [ "primary_key", "unique", "required" ], "range": { "min": 1, "max": 12 } }, { "name": "total_volume", "description": "Total transaction volume in euros for this merchant-month.
", "type": "number(quantity)", "units": "EUR", "constraints": [ "required" ], "range": { "min": 91877.05, "max": 438023.59 } }, { "name": "fraud_volume", "description": "Total volume of transactions flagged as fraudulent disputes, in euros.
", "type": "number(quantity)", "units": "EUR", "constraints": [ "required" ], "range": { "min": 5612.78, "max": 42617.6 } }, { "name": "fraud_percent", "description": "Fraud rate as a percentage: fraud_volume / total_volume * 100.
", "type": "number(quantity)", "units": "%", "constraints": [ "required" ], "range": { "min": 6.09, "max": 11.62 } }, { "name": "monthly_volume", "description": "Binned total_volume matching the fee rule volume ranges.
", "type": "enum", "constraints": [ "required" ], "values": [ "<100k", "100k-1m", "1m-5m", ">5m" ], "value_labels": { "100k-1m": "100k to 1m euros", "1m-5m": "1m to 5m euros", "<100k": "Under 100k euros", ">5m": "Over 5m euros" } } ] }, { "name": "merchant_category_codes", "description": "Lookup table of Merchant Category Codes (MCCs). MCCs are four-digit codes assigned by card networks to classify a merchant's business type.
", "source": { "parquet": "data/merchant_category_codes.parquet" }, "columns": [ { "name": "mcc", "description": "Four-digit Merchant Category Code.
", "type": "number(id)", "constraints": [ "primary_key", "unique", "required" ], "referenced_by": [ { "table": "merchants", "column": "merchant_category_code" } ], "examples": [ 742, 3286, 3679, 5732, 9950 ] }, { "name": "description", "description": "Human-readable description of the merchant category.
", "type": "string", "constraints": [ "required" ], "examples": [ "Concrete Work Contractors", "Eating Places Restaurants", "Industrial Supplies", "Recreation Services", "Veterinary Services" ] } ] } ], "relationships": [ { "description": "Each payment belongs to one merchant.
", "cardinality": "many-to-one", "declared_cardinality": "many-to-one", "pairs": [ { "left": { "table": "payments", "column": "merchant" }, "right": { "table": "merchants", "column": "merchant" } } ], "join": "payments.merchant = merchants.merchant" }, { "description": "Each merchant has one or more acquirers.
", "cardinality": "many-to-one", "declared_cardinality": "one-to-many", "pairs": [ { "left": { "table": "merchant_acquirers", "column": "merchant" }, "right": { "table": "merchants", "column": "merchant" } } ], "join": "merchants.merchant = merchant_acquirers.merchant" }, { "description": "Each merchant-acquirer references one acquirer.
", "cardinality": "many-to-one", "declared_cardinality": "many-to-one", "pairs": [ { "left": { "table": "merchant_acquirers", "column": "acquirer" }, "right": { "table": "acquirer_countries", "column": "acquirer" } } ], "join": "merchant_acquirers.acquirer = acquirer_countries.acquirer" }, { "description": "Each merchant has monthly aggregates for each active month.
", "cardinality": "many-to-one", "declared_cardinality": "one-to-many", "pairs": [ { "left": { "table": "merchant_months", "column": "merchant" }, "right": { "table": "merchants", "column": "merchant" } } ], "join": "merchants.merchant = merchant_months.merchant" }, { "description": "Each merchant has one merchant category code.
", "cardinality": "many-to-one", "declared_cardinality": "many-to-one", "pairs": [ { "left": { "table": "merchants", "column": "merchant_category_code" }, "right": { "table": "merchant_category_codes", "column": "mcc" } } ], "join": "merchants.merchant_category_code = merchant_category_codes.mcc" } ], "glossary": [ { "term": "acquirer", "definition": "The acquiring bank that processes a merchant's card transactions and settles funds. Also called the \"acquiring bank\" or \"merchant bank.\"
" }, { "term": "card scheme", "definition": "The card network (e.g. GlobalCard, NexPay) that sets rules and interchange rates for transactions on its network.
" }, { "term": "ACI", "definition": "Authorization Characteristics Indicator. A code that identifies the transaction flow submitted to the acquirer (e.g. card-present vs card-not-present, authenticated vs non-authenticated).
" }, { "term": "MCC", "definition": "Merchant Category Code. A four-digit code assigned by card networks to classify a merchant's business type, used for risk assessment, fraud detection, and fee determination.
" }, { "term": "intracountry", "definition": "A domestic transaction where the card-issuing country and the acquiring country are the same. Intracountry transactions typically have lower fees than cross-border transactions.
" }, { "term": "BIN", "definition": "Bank Identification Number. The first six to eight digits of a card number that identify the issuing bank.
" }, { "term": "POS", "definition": "Point of Sale. An in-person or in-store transaction, as opposed to an online (ecommerce) transaction.
" }, { "term": "3-D Secure", "definition": "A payment security protocol that adds an extra authentication step for online card-not-present transactions, reducing fraud risk.
" }, { "term": "chargeback", "definition": "A reversal of a transaction initiated by the cardholder's issuing bank, typically due to a dispute or fraud claim.
" }, { "term": "capture delay", "definition": "The number of days between authorization and settlement of a transaction. Faster capture is generally more expensive.
" } ] }