P&G Click Predict Innovate

1616 Registered Allowed team size: 1 - 5
1616 Registered Allowed team size: 1 - 5

Winners are announced.

idea phase
starts on:
Apr 18, 2018, 12:30 PM UTC (UTC)
ends on:
May 20, 2018, 06:25 PM UTC (UTC)
starts on:
May 22, 2018, 11:30 AM UTC (UTC)
ends on:
Jun 10, 2018, 06:25 PM UTC (UTC)



The image recognition market is exploding behind growth in smartphones, tech adoption across industries, and demand for data analytics driven by image recognition in media, brand building, and investments by tech companies in open source.

What Does P&G Want?

  • Pilot partners who work with image recognition with a front end solution to improve tracking and sale of products in retail stores through machine learning and analytics, based on visibility.
  • Support on training of AI based image recognition via photo library and Pilot/Proof of Concept with Distributor covered stores.

What's in it for you?

  • Chance to conduct a breakthrough innovation pilot with global applicability using your image recognition model
  • Support on pilot design, execution, and funding!
  • Cash prizes worth INR 3 Lacs!

How to proceed?

1) Solve one of the problem statements given below to win cash prizes and/or get a chance to work with P&G on an image recognition model with global impact.

2) There are two phases in this campaign. In the first phase, before May 14th, you need to submit a synopsis of your idea and how you plan to implement it. In the second phase, if shortlisted, you need to build a functional prototype of your idea.

Submission Instructions

  • You are expected to submit the solution file along with a brief description of how the given solution was implemented. This description should also contain some metadata about the datasets that you used like number of images, number of labels; etc.
  • For 'Object Detection', attach screenshots of at least 5 result images showing bounding boxes over products along with their category labels.
  • For 'Recommendation System', provide recommendations for at least 5 test cases.
  • Make sure that files of both the challenges are kept in seperate folders, then zip both the folders and upload.

About P&G

P&G is one of the largest and amongst the fastest growing consumer goods companies. Established in 1837, P&G now serves over 4.6 billion consumers across the globe. Its presence pans across the Beauty & Grooming segment, the Household Care segment as well as the Health & Well Being segment, with trusted brands that are household names. These include Vicks, Ariel, Tide, Whisper, Olay, Gillette, Ambipur, Pampers, Pantene, Oral-B, Head & Shoulders, Wella and Duracell. Superior product propositions and technological innovations have enabled P&G to achieve market leadership in a majority of categories it is present in.

enter image description here


An example data set for 'Object Detection' will be uploaded on this page in the coming week. However, if you find other data sets that are relevant or better, please go ahead and use them.

The example data set for 'Recommendation System' has been given under the description.

Object Detection

Visibility norms of products in retail stores dictate how and where they should be positioned in the store, to achieve optimum visibility and increased sales. Today the process for validating visibility norms in Traditional Trade is based on audit activities conducted in a subset of stores via external agencies leading to lack of timely actionable insights. Manual audit within a store via a Sales Rep is also a biased view due to same individual doing audit and taking action. Using object detection, create a system to track and validate visibility norms in all P&G Stores in a fast, cost-effective, unbiased, and automated way.

You are expected to create deep learning models that detect multiple products from shelf images and classify them into different categories as given in the dataset. Detected products should be categorized into 4 categories, mentioned in the dataset. In the dataset, all images are divided in 4 folders, where folder name is the category of all products inside that folder. Bounding box coordinates for each product are also provided, that can be used for detecting product from shelf images. You also need to calculate the quantity of that particular product or product category in the image or shop.

Also make sure that you develop your solution using deep learning. Submissions implementing OpenCV’s built-in object detection will not be considered.

The data set for Object Detection can be accessed here. We have added to the data set given last week. Another set of annotated images can be found here. Please download both.

Recommendation System

Sales Representatives of P&G go from store to store, asking retailers to stock up on P&G products basis availability of different categories of products. Average call time of a Sales Rep within a store is 20 mins. Today a majority of the Sales Reps’ time is spent in asking retailers about availability of products and reviewing what to sell, as opposed to executing the sale . Any intelligent recommendations he does get on his Selling Device are based on historical sales data. There is no consideration for product availability within the store at that time, which wastes a lot of time.

You are expected to create a product recommendation system using machine learning and the given dataset. You are free to use both content based filtering or collaborative filtering. Given dataset contains a CSV file with user_id, product_id and rating of product. Based on that, you have to recommend products to users. You are also free to use any other publicly available datasets, if you want.

If your model is selected, you will later get to work with P&G’s dataset as part of the project and build a recommendation system relevant to P&G’s products.

Please click here to access the example data set. Column 1 is the User ID, Column 3 is Rating, and Column 4 is Product ID. Column 2 is irrelevant.

Open Innovation

Create any image recognition based AI system that you feel will benefit P&G's retail strategy in the emerging markets.


Main Prizes
Project with P&G: Worth $50 Thousand

Select teams will get to work with P&G and the brand's products to build an image recognition model for the company to improve tracking and better sale of products in retail stores through machine learning and analytics.

1st Prize
INR 1,50,000
2nd Prize
INR 1,00,000

Social Share

Help & Support

Please contact event admin
HackerEarth Support at support@hackerearth.com
View All Notifications