Role of Machine Learning in Inventory Optimization using Time-series Forecasting

EasyChair Preprint 5930

Abstract

A key concern for manufacturers today is to maintain optimum inventory levels to drive business growth with better prediction of future sales. With rapid advancements in analytics and machine learning (ML), companies can now proactively examine master and transactional data in near real-time and use the insights derived to plug the gaps and revenue losses. ML algorithms and the models they are based on, excel at finding anomalies, patterns, and predictive insights in large data sets. Predictive analytics can anticipate any spikes or dips in demand and suggest which items should be replenished when along with quantity and location/store. I have developed an ML model to forecast sales demand to help optimize inventory and save significant cost due to high or short inventory caused by inaccurate demands. The model also looks at the return orders data to optimize the returns, thereby resulting in customer satisfaction and cost reduction.

Keyphrases: Inventory Optimization, machine learning, return order, sale forecasting prediction, supply chain

@booklet{EasyChair:5930,
  author    = {Archit Bansal},
  title     = {Role of Machine Learning in Inventory Optimization using Time-series Forecasting},
  howpublished = {EasyChair Preprint 5930},
  year      = {EasyChair, 2021}}