Forecasting the Inventory Demand for Asset Management Team

The goal of this project is to apply what I have learned through my coursework in data science program to help Asset Management team at Raytheon find a solution to predict the demand of
the assets. The Asset Management team manages all the IT equipment for the Program Engagement Leads and Project Managers within the organization. In this research, my main goal is to determine the potential demand of the assets, from which to propose measures as well as an overview of the inventory demand, helping the asset management team reduce risk of over-purchasing and excess inventory. Moreover, it also helps the asset management team improve operational efficiency as well as ensure enough asset needs in the coming time. My objective is to conduct a few machine learning models such as binary logistic regression (LR), linear support vector machine (SVM), decision tree (DT) models that can predict whether the assets will be in demand or not based on the business orientation, program deployment strategies, and the deployment history/trend. Then, I will evaluate the accuracy of models and determine the best model for predicting the demand probability of an asset. By understanding the asset demands, the team could also effectively manage inventory, plan deployment, and optimize the supply chain.