The purpose of this document is to provide an overview of the demand forecasting solution and outline the importance of employing various ML-based ARIMA timeseries models with improvement approaches to achieve efficient forecast results to help solve business challenges. This paper also uncovers ways to handle the impact of events like COVID-19 and holidays on forecast and explains how high and low volumes are handled. The evaluation of the best suited time series to create forecasts on both count and rate-based methods have also been highlighted in this paper.