Behavioral product promotions to motivate the shopper to purchase

                        Most of the present product promotion engines are going to work based on the events. That means, the events are predefined in the e-Commerce system and when the event occurs the rule associated to that event will get evaluate. If the rule evaluates as true, then the promotion will be applied. For example, the event configured as “placing an order” and the rule configured as “total order amount exceeds > $100” then apply the promotion $10. If you look at the example promotion configuration, the promotion will be applied to users who meet the rule.

                    Now, we will see how we can enhance the promotions engine to bring the promotions to the shoppers based on the behavior on the website.  If you predict the behavior of the shopper, then you can bring the personalized product promotions in real time and then you will see boost in online sales.  In this way you can predict the loyal customer and target the better promotions to them to make them as returning customers.

                     The below block diagram depicts the parameters which will be used to predict the shopper behavior and display the personalized product promotions to the user.

                                                           In the above diagram we are concentrating on the parameters which will give us the scope to predict the loyal customer. The loyal customers are the ones who will be the returning customers, who are the ones most often closing the deals. So, we need to provide better promotions to those customers than the others. For example customer want to purchase “iPhone 5s”. Let us see how is the user journey will be to purchase the product.

1. Product Search: Generally, if the user want to purchase any product, the customer will do lot of analysis on the product. Here the user journey will start from the searching of the “i Phone 5S”. We are going to keep track of those searching parameters on the website.
2. Click Through Behavior: After searching of the product and finding the right product, we are going to keep track of the customer browsing navigation on the website and the time spending on the website. Usually,
   1. The customers will get into the search results of the “i Phone 5s” and choose the product.
   2. Spends lot of time to read the product details. Keep track of the time spending on the “i Phone 5S” product detail page.
   3. Spends time on the technical feature/specifications tab. Keep track of time spending and the click through navigation of specifications tab.
   4. Some times the shopper uses product comparison feature to compare the likely products. Keep track of this.
   5. Keep track of click through behavior of product recommendations.
3. Order Purchase History: As user is logged in,
   1. Bring the previously purchased history to see how much orders the shopper is placed.
   2. Bring the total number of visits. This will tell us how often the user is visiting the site and closing the deals.

                        All the collected parameters will be send to the predictive analysis system which will be using the “Machine Learning Techniques” to predict the behavior and  the loyal of the shopper towards purchasing of “i Phone 5S”. Then we can bring the real time promotions to the user to motivate to purchase “i Phone 5S”. These personalized promotions will be derived real time and valuable to the loyal customers who are providing more revenue to ones business.

The above analysis is best of my knowledge. If any one wants to add more information add as part of comments.

About Siva Prasad Rao Janapati

Siva Janapati is an Architect with experience in building Cloud Native Microservices architectures, Reactive Systems, Large scale distributed systems, and Serverless Systems. Siva has hands-on in architecture, design, and implementation of scalable systems using Cloud, Java, Go lang, Apache Kafka, Apache Solr, Spring, Spring Boot, Lightbend reactive tech stack, APIGEE edge & on-premise and other open-source, proprietary technologies. Expertise working with and building RESTful, GraphQL APIs. He has successfully delivered multiple applications in retail, telco, and financial services domains. He manages the GitHub(https://github.com/2013techsmarts) where he put the source code of his work related to his blog posts.