© 2019 by Santanu Bhattacharjee.

Online Order Management - Cognitive Solution

Retail

Use Cases

Showing preferred car models to customers and predicting propensity score for conversion

Propensity Model

+

Attribution Model

Getting content attribution at page and component level from user journey analysis

+

Drop-off Model

Predicting customer's next activity and possible drop-off from the website

Summary

The retail food chain used to serve a fixed number of orders in a day to its customers because of its system restriction. As a result, the resources (labor, storage) were not fully utilized to its capacity. The project was aimed at removing that restriction by introducing resource optimization methods. In addition, the order prediction model was developed for helping store managers to plan his/her resources in advance.

Solution

The application was based on two models: Order Prediction Model and Resource Optimisation model.  

Order Prediction Model:

 

Orders data (by day and slot) was collected for the last many years from the client. In addition, few other macro-economic attributes (like weather/events near the store location) were collected which would have influenced intake orders in past. A time-series analysis was performed to get future orders' count.

 

Resource Optimisation Model:

The objective function of this optimization problem was to maximize the online intake orders and the constraints were defined considering limited resources including labor hours, storage capacity in orders provisioning area. Linear programming model was used as a solution for this problem statement.

Algorithm Flow

Tools & Technologies

  • Anaconda Distribution

  • Python 3.6.3

  • CSV data format

  • NPM HTTP Server

  • Web Application

  • SAP Hybris

Python Libraries & Frameworks

  • SciKit Learn

  • Numpy

  • Pandas

  • Pulp

  • Pickle

  • Flask

  • Json