Sales Forecasting Models for Paint and Furnishing Products

Abstract

"

This project focuses on creating machine learning and deep learning algorithms or models to forecast sales quantity with higher accuracy for the next 12 months. The current forecast process is not as accurate as desirable, which can be seen, first, on the company financial side and, secondly, on a sold unit delivery time, which has a direct impact on the customer experience. An improved forecasting approach would help the sales and operations planning team of the case company to further develop a more accurate production planning and more optimised material stocks in order to cope and overcome the current problem.

The main data sources of this project consist of sales data (internal) and national holidays (external). The outcome of this study is an improved 12-month sales forecasting approach, which consists of recommendations for a new forecast process together with specified actions. By implementing the recommended process and actions, the case company would be able to improve its sales forecast accuracy, which will further improve the efficiency of the Sales and Operation Planning Process. "