Published Paper Details:

Population expansion, climate change, and digitization are driving up food demand faster than the country's economic growth. Perishable goods are handled more frequently by the food-related businesses, such as fast food chains, restaurants, canteens, and catering services. Organizing consumer food orders is one of the main problems faced by the food-related industry. Occasionally, inaccurate ordering estimates might result in either too much or too little food, wasting both food and raw materials and cutting into profits for the business. In order to ensure sustainable food systems and efficient resource allocation, food demand forecast is crucial. In an era of rapidly rising populations and shifting consumer tastes, accurate food demand forecasting is critical to minimizing food waste, optimizing performance, and enhancing food security. In this quest, machine learning algorithms have proven to be effective tools, with the ability to produce forecasts that are more dynamic and exact. In order to analyze the historical data and forecast the consumption for the upcoming months, we employed the decision tree algorithm. Along with internal variables, machine learning models also incorporate external variables like social events and economic indices.