E-commerce analytics: Product Recommendation Engines

Have you ever come across a business offering you more when you have already purchased one product or service? I get offers even from my hairdresser. Saloons offer head massages or facials when you go for a haircut. Many times, offers to get converted to revenue for saloons. This is a perfect daily life example of product/service recommendations. We could see such relevant offers more when we purchase products online from Amazon, Flipkart, etc.

One of the premier examples of a product recommender is a contest organized by Netflix with a prize money of $1,00,000. One can easily get an idea about the business benefit Netflix might have earned by paying a huge amount as prize money for improving their movie recommendation engine.

Introduction

In layman’s terms, the outcome of this technique is a simple set of product/service rules based on customer product purchasing behavior. e.g. if a customer bought milk, then will he go to buy eggs too? In this data analytics technique, what is being purchased with what is been analyzed? Is buying one specific item increases the chances of buying other items? We will explore the business grocery dataset to get such answers.

Product recommendation engines are also known by a few other names such as Apriori Algorithm, Affinity Analysis, Association rules, and Market basket analysis. We will not go into technical details of how it will work in this blog. The objective is to make aware smaller & medium organizations about the topic & how it adds value to the business.

Why is this technique useful?

Acquiring a new customer is always more costly for any business than keeping an existing customer. By this technique, businesses can increase revenue from existing customers on the basis of customer product buying rules. Product & services up-selling and cross-selling can be one of the very intuitive use cases of basket analysis. In addition to these product combos, shop floor/website layout can also be suggested accordingly. Last but not least, products can be suggested based on real-time purchasing behavior.

Technical Definitions

Here are the basic technical terms useful in this analysis are as below

• Support: The fraction of which our itemset occurs in our dataset.
• Confidence: Probability that a rule is correct for a new transaction with items on the left.
• Lift: The ratio by which the confidence of a rule exceeds the expected confidence.
  Note: if the lift is 1 it indicates that the items on the left and right are independent.

Do not worry if these terms go off your head. You will get over them soon!

R shiny playground

R shiny toy product has been used for demonstration purposes. R — an open source tool can easily be downloadable from the cran website if you want to learn more about it, but it is not required for this demo purpose. We used an R package called ‘rules’ from Michael Hahsler who has implemented this algorithm in R. There’s public data of buying records in a grocery store which will be used for this exercise using the Shiny Demo App.

How to use R shiny Demo product

Step 1: Open R Shiny App

Step 2: Upload grocery dataset public data (If you have your own dataset, make sure to change the format as per the sample dataset)

Step 3: Select input data features

a) Unselect header as provided dataset does not contain a header ( if your dataset has a header, please select accordingly)

b) Select space separator as sample dataset having space separation.

c) Keep all default values as it is for now if you find them too technical.

Step 4: Explore shiny app tabs such as top 25 item frequency, basket analysis rules, sorting rules option e.g lift, support, etc.

Step 5: Find out specific product rules e.g select beer from the select product dropdown. All the product rules for the selected products will be displayed under the product combo check. This feature can be used for creating specific product combos.

Step 6 (Optional): if you understand the technical terms mentioned above, try to play with them to see the effect on rules.

Why are E-commerce recommendations important?

For an e-commerce business, recommendation solutions are a boon. It helps them sell more to their customers as the system identifies the items the customers usually like and recommend the products to them at the right time and place. Customers end up buying items that they never had thought of buying initially. This is why recommendation systems are important.

Want to implement such a system in your business? You should be connecting with renowned data analytics consulting services for the same.

Conclusion & business scope

Isn’t it amazing! How ecommerce analytics solutions can provide what customers might need to add to the cart in real-time. This is a very basic toy example of product recommendations based on a rules algorithm. Advanced recommender engines make use of other data points from customer behavior in addition to advanced algorithms such as factorization machines, collaborative filtering, etc. Now you can fairly co-relate how Amazon recommends different products. Any small business can make use of this technique to add value to the business in some other ways:

• Product combo suggestions for a marketing campaign.
• Website or store layout re-alignment e.g if eggs are bought with milk, re-organize accordingly
• Product cross-selling, real-time web/App product recommendations.

We here at DataToBiz with a team of data analytics and machine learning experts can support your business to solve problems by providing an affordable machine-learning platform for your business data. Contact Us for more info.

Parindsheel Dhillon

Co-founder and COO, DataToBiz