E-Commerce Product Recommendation Logs

This dataset provides detailed logs of e-commerce product recommendations, capturing user interactions, engagement outcomes, and algorithm details for each recommendation event. It enables analysis of personalization effectiveness, user behavior, and click-through rates to optimize product discovery and recommendation strategies.

  • last updated 20 Aug 2025
  • by GoMask
The brief that made it

Optimizing recommendation algorithms for higher conversion rates

Sample rows

preview · 8 of 200 rows · all 17 columns
log_idstringengagement_typestringproduct_pricefloatclick_throughbooleanuser_location_countrystringuser_idstringsession_idstringrecommendation_timestampdatetimerecommended_product_idstringrecommendation_rankintegeralgorithm_typestringengagement_timestampdatetimepurchasebooleanproduct_categorystringuser_location_citystringuser_location_statestringdevice_typestring
L0001clicked849.99trueUSAU1001S101A2024-02-14T10:15:22ZP-40211collaborative2024-02-14T10:16:17ZfalseelectronicsSan FranciscoCAdesktop
L0002viewed54.99falseUSAU1002S101B2024-03-22T08:42:11ZP-40552hybridblankfalseapparelChicagoILmobile
L0003purchased299.99trueUKU1003S102C2024-04-05T14:09:03ZP-40831content-based2024-04-05T14:09:55ZtrueelectronicsLondonLondondesktop
L0004ignored129.99falseFranceU1004S103D2024-01-18T17:23:45ZP-41023collaborativeblankfalsehomeParisÎle-de-Francetablet
L0005viewed19.99falseNew ZealandU1005S104E2024-05-03T12:22:08ZP-41244otherblankfalsegardenAucklandAucklandtablet
L0006clicked87.5trueAustraliaU1006S105F2024-03-10T09:35:33ZP-41582hybrid2024-03-10T09:36:14ZfalseapparelSydneyNSWmobile
L0007purchased1499.95trueJapanU1007S106G2024-02-28T15:17:50ZP-41731collaborative2024-02-28T15:18:43ZtrueelectronicsTokyoTokyodesktop
L0008ignored34falseIndiaU1008S107H2023-12-08T13:11:22ZP-41955content-basedblankfalsebeautyMumbaiMHmobile

What the 200 rows show

from the 200-row sample

Purchased (engagement type) stands out: mean product_price is 1,383, against 181.7 for the rest.

  • 51%click_through = true
  • 97.5median product_price
  • 4algorithm types
  • 4device types
  • 6product categories
  • 2median recommendation_rank
Mean product_price by engagement_type200 rows
01,0002,00058.9viewed64 rows345.3clicked81 rows1,383purchased21 rows22.8ignored34 rows
product_price200 rows, in bands of 500
085170162265230202,0003,500product_price →

Median 97.5, from 7.0 to 3,500.

user_location_country200 rows · top 10 of 39 values
  1. USA31
  2. UAE13
  3. Brazil12
  4. Germany11
  5. UK9
  6. South Africa9
  7. China9
  8. Spain9
  9. Australia8
  10. New Zealand7
17 columns by typefrom the column list below
  • string 11
  • integer 1
  • float 1
  • datetime 2
  • boolean 2

Columns

17 columns in four groups
blueprint · 17 columns
columntypedescriptionexample
Text 11 columns
log_idstringUnique identifier for each recommendation log entryuniqueL0001
user_idstringUnique identifier for the user receiving recommendationsU1001
session_idstringIdentifier for the user's session during which recommendations were servedS101A
recommended_product_idstringUnique identifier for the product recommended to the userP-4021
algorithm_typestringType or name of the recommendation algorithm used (e.g., collaborative, content-based, hybrid)collaborative · content-based · hybrid · othercollaborative
engagement_typestringType of user engagement with the recommendation (e.g., viewed, clicked, purchased, ignored)viewed · clicked · purchased · ignoredclicked
product_categorystringCategory of the recommended product (e.g., electronics, apparel, home)6 categories · optionalelectronics
user_location_citystringCity of the user at the time of recommendation (if available)optionalSan Francisco
user_location_statestringState or region of the user at the time of recommendation (if available)optionalCA
user_location_countrystringCountry of the user at the time of recommendation (if available)optionalUSA
device_typestringType of device used by the user (e.g., desktop, mobile, tablet)desktop · mobile · tablet · other · optionaldesktop
Numbers 2 columns
recommendation_rankintegerRank or position of the product in the recommendation list (e.g., 1 for top recommendation)1 or more1
product_pricefloatPrice of the recommended product at the time of recommendation0 or more · optional849.99
Dates and times 2 columns
recommendation_timestampdatetimeDate and time when the recommendation was generated and shown to the user2024-02-14T10:15:22Z
engagement_timestampdatetimeDate and time when the user engaged with the recommended product (if applicable)optional2024-02-14T10:16:17Z
True or false 2 columns
click_throughbooleanIndicates whether the user clicked on the recommended producttrue
purchasebooleanIndicates whether the user purchased the recommended productfalse

Use it for

  • click through51%102 of 200 rowsmean product price by…58.9view…345.3clic…1.4kpurc…22.8igno…

    An e-commerce dashboard

    The click_through rate, product_price by engagement_type and a breakdown of user_location_country. Excel, Power BI or Tableau.

  • Why do the 21 purchased rows have a mean product_price of 1,383?

    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 logs with user_id, session_id and recommendation_timestamp to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 17 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 dataset200 rows17 columns
Yours1,000 rows17 columnsuser_location_city: UK only

blueprint · e-commerce-product-recommendation-logs

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 17 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
  • User ID and recommendation set tracked
  • Clickthrough and engagement logged
  • Product category and attributes included
  • Personalization score computed
Rows
Open the blueprint in Data Factory

1 credit per row. Preview 20 rows free. Buy rows for the full run.

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

More in E-commerce

Browse all
Also in E-commerceCustomer Wishlist Item TrendsShopping Cart Abandonment InsightsOnline Retail Product Return AnalyticsAll 1,966 datasets

What should your data show?

Preview 20 rows free
No signup. No card.