Browse Prior Art Database

Online Recommendations for Offline Shopping

IP.com Disclosure Number: IPCOM000247795D
Publication Date: 2016-Oct-06
Document File: 2 page(s) / 30K

Publishing Venue

The IP.com Prior Art Database

Abstract

We propose a method which will be offered as a service from e-commerce sites to show information about most bought and most searched products at a physical store where a user is doing offline shopping.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 47% of the total text.

Page 01 of 2

Online Recommendations for Offline Shopping


Many user's have a common behavior of looking for online deals while doing offline shopping to get best deals. The prices of products are compared for offline and online and the cheapest medium is chosen to place the order. Online providers such as Amazon, Flipkart currently consider only online data and use it to recommend products when user is browsing through products online. The offline behavior of a user at a store is not currently considered. With our belief that many user's also look for online deals while shopping outside, we propose a method where ecommerce sites can use offline data to provide product recommendations so that user experience is improved.

The advantage of this method is that e-commerce sites can convert more offline customers to buy online and push more deals online based on offline shopping behavior of many users at a particular location.

E-commerce sites currently consider only online data to show recommendations. But with new behavior of users doing online search while doing offline shopping, e-commerce applications may change their recommendation algorithm to push more related deals to the user based on location(store) where users are doing offline shopping.

The new recommendation algorithm is explained below:


1. When a user is doing search on a e-commerce site, the current location of the user is retrieved.

2. The location data is compared with location of any nearby shops or retail outlets to see if user is doing shopping at a physical location . If location matches, the new recommendation algorithm kicks in.

3. The search keywords and online orders at a particular shopping location are tracked to find the products that are being searched/ordered.

4. The new algorithm groups the products based on a store location and sorts them according to various parameters like most frequently ordered from that location, most bought deal from the location, most searched product, available products at that store etc.

5. Now when a user visits that location and opens e-commerce application, all the data which was collected above is shown to the user.

6. The recommendations are not shown just based on user's browsing behavior but (many) customer's behavior at a particular shopping location.

7. If there are more online orders from a store location, the recommendation algorithm can show more related products if a store is identified. For example, if the shop is identified as Reliance Electronics, all electronic goods can be recommended when a user is doing shopping at Reliance Electronics.

Advantage of the New Recommendation Algorithm:


1. The recommendations to user is based on the most bought or most searched products at a shopping location. For example: If a user goes to shopping to buy Winter Jacket in a shop, the e-commerce site will show the best jacket deals based on the other user's past browsing or search history at the store location. The application can also recomm...