Enhancing Raw Material Demand Planning In Restaurants Through Time Series Analysis

Abstract

According to the Food and Agriculture Organization (FAO) of the United Nations, an estimated 1.3 billion tons of food are wasted globally each year, which is equivalent to one-third of all food produced for human consumption. The economic value of this wasted food is estimated at around $1 trillion. There have been some studies and projects aimed at developing techniques for the Supply chain for Raw materials using various machine learning and deep learning techniques. However, there is still room for improvement in the accuracy and efficiency of these techniques.

In this approach is to develop a system to recommend the quantity of raw materials to be purchased to reduce the stockouts and overstocking by using various machine learning techniques that involves analyzing data on food consumption and waste, identifying patterns and trends in the data, and using machine learning algorithms to develop predictive models that can help reduce food waste. The optimization will be done to the model using techniques such as cross-validation and hyper parameter tuning. The accuracy of the models is evaluated using metrics such as MAE, MSE, RMSE and R2 SCORE. This system will improve overall customer satisfaction, and restaurant profit and reduces the wastage of raw materials.