{ "fetched_at": "2026-10-22T10:37:56Z", "source_url": "https://www.kaggle.com/competitions/hack-reduce-dunnhumby-hackathon/data", "pages": [ { "name": "Description", "content": "

Predict how successful a product will be after its launch

\r\n

hack/reduce and dunnhumby announce the Product launch challenge, as part of a one day hackathon. This competition asks you to predict how successful each of a number of product launches will be 26 weeks after the launch, based only on information up to the 13th week after the launch.

\r\n

\"Forecast\"

\r\n

The training set and question set each contain by week for each launch:

\r\n\r\n

Competition begins: Saturday, May 11, 9am EDT (1:00pm UTC)
Competition ends: Saturday, May 11, 7pm EDT (11:00pm UTC)

\r\n

This competition awards 25% the ranking points of a standard competition, but does not count towards tiers. The top remote participant in the Kaggle competition will receive a \"Prize Winner\" achievement on their profile, in addition to the three local winners.

", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "

Prediction accuracy will be evaluated based on the root mean square logarithmic error:

\r\n

\"\"

\r\n

Where:

\r\n
    \r\n
  1. i is a product
    2. \r\n
  2. n is the total number of products
    3. \r\n
  3. p is the predicted sales volume (units sold in week 26)
    4. \r\n
  4. a is the actual sales volume (units sold in week 26)
    5. \r\n
\r\n

Note: the metric is calculated using the natural log.

\r\n

We have chosen a log-based metric to minimise the effects of outliers and reward accurate predictions, without overly penalising predictions that are far from the actual.

", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "\r\n\t\r\n

One account per participant

\r\n

You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.

\r\n

No private sharing outside teams

\r\n

\r\n Privately sharing code or data outside of teams is not permitted.\r\n It's okay to share code if made available to all participants on the forums.\r\n

\r\n

Team Mergers

\r\n

Team mergers are not allowed in this competition.

\r\n\r\n

Team Limits

\r\n

There is no maximum team size.

\r\n

Submission Limits

\r\n

You may submit a maximum of 20 entries per day.

\r\n

You may select up to 2 final submissions for judging.

\r\n

Competition Timeline

\r\n

Start Date: 5/11/2013 1:00 PM UTC

\r\n

Merger Deadline: None

\r\n

Entry Deadline: None

\r\n

End Date: 5/11/2013 11:00 PM UTC

\r\n\t\r\n

I agree to the competition rules and eligibility release, in the event I wish to receive a prize. 

", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "

Update - the data has been removed to comply with the client's data sharing policy. We apologize for any inconvenience.

\r\n

This ZIP files a training set of 18 columns and 71969 rows (including header).  These represent a historical sample of 2768 previous product launches with full information for all 26 weeks of launch that can be used to create your models.

\r\n

The ZIP file also contains a question set of 18 columns and 28315 rows (including header).  These represent the set of 1089 product launches that we want you to predict unit sales in week 26, and only contain sales information up to week 13.  (The stores selling information is for the full 26 weeks as store distribution would be known in advance, and a key factor in predicting future sales).

\r\n

Both of these files are in the same format, and contain the following columns:

\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n
ColumnDescription
 Product_Launch_Id A unique ID for each product launch.  Is repeated for each week of the launch
 Product_Category A text description of the type of product
 Weeks_Since_Launch The number of weeks since the product was first sold.  (integer between 1 and 26)
 Stores_Selling The number of different stores that sold the product in that week.  (note that this is up to week 26 even for the question set, as the business would plan store distribution in advance)
 Units_that_sold_that_week The units sold that week.  The field that we want you to predict for week 26.
 Distinct_Customers_Buying_At_Least_Once_Cumulative The distinct number of customers who have made at least one purchase of the product up to the given week.
 Distinct_Customers_Buying_More_Than_Once_Cumulative The distinct number of customers who have bought the product on at least two occasions.  (Can be used to infer repeat rate).  Cumulative - up to the given week.
 Cumulative_Units_Sold_To_Convenience_At_Home_CustomersThe cumulative units sold, up to the given week, for customers that are in the appropriate customer segment.
 Cumulative_Units_Sold_To_Family_Focussed_Customers The cumulative units sold, up to the given week, for customers that are in the appropriate customer segment.
 Cumulative_Units_Sold_To_Finest_Customers The cumulative units sold, up to the given week, for customers that are in the appropriate customer segment.
 Cumulative_Units_Sold_To_Grab_and_Go_Customers The cumulative units sold, up to the given week, for customers that are in the appropriate customer segment.
 Cumulative_Units_Sold_To_Shoppers_On_A_Budget The cumulative units sold, up to the given week, for customers that are in the appropriate customer segment.
 Cumulative_Units_Sold_To_Traditional_Homes_Customers The cumulative units sold, up to the given week, for customers that are in the appropriate customer segment.
 Cumulative_Units_Sold_To_Watching_The_Waistline_Customers The cumulative units sold, up to the given week, for customers that are in the appropriate customer segment.
 Cumulative_Units_Sold_To_Least_Price_Sensitive_Customers The cumulative units sold, up to the given week, for customers that are in the appropriate customer segment.
 Cumulative_Units_Sold_To_Price_Sensitive_Customers The cumulative units sold, up to the given week, for customers that are in the appropriate customer segment.
 Cumulative_Units_Sold_To_Splurge_And_Save_Customers The cumulative units sold, up to the given week, for customers that are in the appropriate customer segment.
 Cumulative_Units_Sold_To_Very_Price_Sensitive_Customers The cumulative units sold, up to the given week, for customers that are in the appropriate customer segment.
\r\n

This competition now uses an improved parser. The new submission format has 2 columns: 

\r\n

Product_Launch_Id: Product Launch Id for given prediction

\r\n

Units_that_sold_that_week: Predicted number of units sold in week 26.

\r\n

Please download and refer the sample format.

", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Prizes", "content": "

Prizes

\r\n

Cash Prizes - Cambridge hack/reduce venue contestants only (prizes per team):

\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n
\r\n

First Prize

\r\n		\r\n

$2,500

\r\n
\r\n

Second Prize

\r\n		\r\n

$1,000

\r\n
\r\n

Third Prize

\r\n		\r\n

$500

\r\n
\r\n

Cash prize - best remote contestant:

\r\n

First Remote Prize - $500

", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }