Product Recommendation Dataset

This dataset provides a detailed, transaction-level view of customer shopping behavior, including customer profiles, product details, session context, and the impact of personalized product recommendations. It is ideal for developing and evaluating recommendation systems, analyzing sales conversion, and understanding the effectiveness of targeted offers in retail environments.

  • opened 7 times
  • last updated 12 Jul 2025
  • by GoMask
The brief that made it

Building and evaluating personalized product recommendation engines

Sample rows

preview · 8 of 120 rows · all 32 columns
customer_idstringcustomer_loyalty_tierstringdiscount_amountfloatis_discount_appliedbooleanshipping_countrystringcustomer_emailstringcustomer_first_namestringcustomer_last_namestringcustomer_genderstringcustomer_birthdatedatecustomer_registration_datedateproduct_idstringproduct_namestringproduct_categorystringproduct_brandstringproduct_pricefloattransaction_idstringtransaction_datetimedatetimequantityintegertotal_amountfloatpayment_methodstringrecommendation_shownbooleanrecommended_product_idstringrecommendation_acceptedbooleansession_idstringdevice_typestringsession_start_datetimedatetimesession_end_datetimedatetimeshipping_street_addressstringshipping_citystringshipping_statestringshipping_postal_codestring
CUST0001gold20trueUSAalex.jones_01@gmail.comAlexJonesmale1986-03-142019-07-21PROD1001Smart Fitness WatchElectronicsFitPro199.99TXN000000012023-04-14T10:08:231179.99credit_cardtruePROD1002falseSID202304141008desktop2023-04-14T10:02:512023-04-14T10:17:06123 Park AveNew YorkNY10016
CUST0002silver0falseUSAcarla.mendez+shop@outlook.comCarlaMendezfemale1990-06-252021-02-03PROD1013Resistance Bands SetFitnessActivePlus35TXN000000022023-02-16T19:45:00270debit_cardfalseblankblankSID202302161944mobile2023-02-16T19:40:122023-02-16T19:54:38742 Parkside DriveSan DiegoCA92103
CUST0003platinum34.5trueNetherlandsstefan.van.der.berg@ziggo.nlStefanvan der Bergmale1974-02-182017-11-10PROD1022Espresso Coffee MakerHome AppliancesBrewMaster179.5TXN000000032023-01-28T13:32:141145bank_transferfalseblankblankSID202301281331desktop2023-01-28T13:24:002023-01-28T13:38:45Grote Markt 88Amsterdamblank1012EZ
CUST0004none0falseIndiapriya.singh1997@gmail.comPriyaSinghfemale1997-11-102022-06-28PROD1017Wireless EarbudsElectronicsSoundFlex89.99TXN000000042023-05-09T21:06:19189.99paypaltruePROD1020falseSID202305092105mobile2023-05-09T20:58:012023-05-09T21:14:34B-19 DLF Phase 1GurgaonHaryana122002
CUST0005gold25trueUKhannah_smith@icloud.comHannahSmithfemale1983-04-222018-05-14PROD1007Premium Yoga MatFitnessActivePlus55TXN000000052023-03-19T07:21:46285credit_cardfalseblankblankSID202303190720tablet2023-03-19T07:19:102023-03-19T07:35:5924 Oxford StLondonblankW1D1LT
CUST0006silver5trueMexicogustav.herrera@correo.com.mxGustavHerreramale1996-09-112020-11-02PROD1012Gaming Mouse X9GamingGameTech49.99TXN000000062023-04-01T17:44:10144.99debit_cardtruePROD1018falseSID202304011743desktop2023-04-01T17:40:002023-04-01T17:55:13Av. Insurgentes 123Mexico CityCDMX01020
CUST0007none0falseblanklucy.brown+shopper@gmail.comLucyBrownfemaleblank2022-12-09PROD1025Gift Card - $50Gift Cardsblank50TXN000000072023-05-01T16:12:14150otherfalseblankblankSID202305011611desktop2023-05-01T16:09:002023-05-01T16:14:20blankblankblankblank
CUST0008platinum100trueSaudi Arabiaahmad.al.saud@gmail.comAhmadAl Saudmale1970-10-042015-10-22PROD10064K LED TV 55 inchElectronicsLuxVision849.99TXN000000082023-04-27T15:30:111749.99bank_transferfalseblankblankSID202304271529desktop2023-04-27T15:18:092023-04-27T15:33:40King Fahd Rd 77Riyadhblank11564

What the 120 rows show

from the 120-row sample

Platinum (customer loyalty tier) stands out: mean discount_amount is 25.8, against 4.2 for the rest.

  • 44%is_discount_applied = true
  • 0.0median discount_amount
  • 3customer genders
  • 3device types
  • 5payment methods
  • 13product categories
Mean discount_amount by customer_loyalty_tier119 rows
020400.0none32 rows3.9silver33 rows7.9gold40 rows25.8platinum14 rows
discount_amount120 rows, in bands of 20
05511010990002060120discount_amount →

Median 0.0, from 0.0 to 120.0.

shipping_country106 rows with a value · 14 left blank
  1. USA18
  2. UK12
  3. Germany7
  4. Singapore6
  5. France6
  6. Canada6
  7. Mexico5
  8. Saudi Arabia5
  9. Argentina5
  10. India4
32 columns by typefrom the column list below
  • string 20
  • integer 1
  • float 3
  • date 2
  • datetime 3
  • boolean 3

Columns

32 columns in four groups
blueprint · 32 columns
columntypedescriptionexample
Text 20 columns
customer_idstringUnique identifier for each customeruniqueCUST0001
customer_emailstringEmail address of the customeruniquealex.jones_01@gmail.com
customer_first_namestringFirst name of the customerAlex
customer_last_namestringLast name of the customerJones
customer_genderstringGender of the customermale · female · other · prefer_not_to_say · optionalmale
customer_loyalty_tierstringLoyalty program tier for the customernone · silver · gold · platinum · optionalgold
product_idstringUnique identifier for each productPROD1001
product_namestringName of the productSmart Fitness Watch
product_categorystringCategory to which the product belongsElectronics
product_brandstringBrand of the productoptionalFitPro
transaction_idstringUnique identifier for each transactionuniqueTXN00000001
payment_methodstringPayment method used for the transaction6 valuescredit_card
recommended_product_idstringProduct ID of the recommended product (if any) shown to the customeroptionalPROD1002
session_idstringUnique identifier for the customer's shopping sessionSID202304141008
device_typestringType of device used during the shopping sessiondesktop · mobile · tablet · other · optionaldesktop
shipping_street_addressstringStreet address for shippingoptional123 Park Ave
shipping_citystringCity for shipping addressoptionalNew York
shipping_statestringState or region for shipping addressoptionalNY
shipping_postal_codestringPostal code for shipping addressoptional10016
shipping_countrystringCountry for shipping addressoptionalUSA
Numbers 4 columns
product_pricefloatUnit price of the product at the time of transaction0 or more199.99
quantityintegerNumber of units of the product purchased in the transaction1 or more1
total_amountfloatTotal amount paid for the transaction (quantity x product_price)0 or more179.99
discount_amountfloatAmount of discount applied to the transaction0 or more · optional20
Dates and times 5 columns
customer_birthdatedateBirthdate of the customeroptional1986-03-14
customer_registration_datedateDate the customer registered on the platform2019-07-21
transaction_datetimedatetimeDate and time when the transaction occurred2023-04-14T10:08:23
session_start_datetimedatetimeStart date and time of the shopping sessionoptional2023-04-14T10:02:51
session_end_datetimedatetimeEnd date and time of the shopping sessionoptional2023-04-14T10:17:06
True or false 3 columns
is_discount_appliedbooleanIndicates if a discount was applied to the transactiontrue
recommendation_shownbooleanIndicates if a product recommendation was shown to the customer during the shopping sessiontrue
recommendation_acceptedbooleanIndicates if the customer accepted the recommendation and purchased the recommended productoptionalfalse

Use it for

  • is discount ap…44%53 of 120 rowsmean discount amount …0.0none3.9silv…7.9gold25.8plat…

    An e-commerce dashboard

    The is_discount_applied rate, discount_amount by customer_loyalty_tier and a breakdown of shipping_country. Excel, Power BI or Tableau.

  • Why do the 14 platinum rows have a mean discount_amount of 25.8?

    A root-cause class exercise

    Hand out the rows and one question. The answer is in the data, not in the brief.

  • A software demo

    Believable customers with customer_email, customer_first_name and customer_last_name to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 32 columns, your size and your rules. See 20 rows before you pay.

Preview 20 rows free

1,000 rows: $1.99 · 10,000: $12.99One-time. No subscription. All prices

This dataset120 rows32 columns
Yours1,000 rows32 columnsshipping_street_address: UK only

blueprint · product-recommendation-dataset

Behind this dataset

Same schema. As many rows as you need.

These 120 rows came out of a blueprint — 32 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.

Rules it was built with
  • Each user must have at least 3 purchase records
  • Products must have a minimum of 2 reviews
  • Transactions over $100 flagged for loyalty points
  • Out-of-stock products are not recommended
Rows
Open the blueprint in Data Factory

1 credit per row. New accounts start with 25 free credits.

Exports
CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence
yours to use, including commercially
API slug
product-recommendation-dataset

More in E-commerce

Browse all
Also in E-commerceE-Commerce Cart Abandonment DataShopping Cart Abandonment InsightsOnline Purchase Refund AnalysisAll 1,954 datasets

What should your data show?

Preview 20 rows free
No signup. No card.