Comparing Prophet and Deep Learning to ARIMA in Forecasting Wholesale Food Prices

TL;DR

This study compares traditional ARIMA, Prophet, and deep learning models like LSTM and CNNs for forecasting wholesale food prices, highlighting the trade-offs between accuracy and ease of use.

Contribution

It provides a comparative analysis of multiple forecasting techniques applied to real-world food price data, including deep learning models and a scalable tool like Prophet.

Findings

ARIMA and LSTM perform similarly in accuracy.

CNN-LSTM combination yields the best accuracy but is time-consuming.

Prophet is fast and user-friendly but less accurate.

Abstract

Setting sale prices correctly is of great importance for firms, and the study and forecast of prices time series is therefore a relevant topic not only from a data science perspective but also from an economic and applicative one. In this paper we examine different techniques to forecast sale prices applied by an Italian food wholesaler, as a step towards the automation of pricing tasks usually taken care by human workforce. We consider ARIMA models and compare them to Prophet, a scalable forecasting tool by Facebook based on a generalized additive model, and to deep learning models exploiting Long Short--Term Memory (LSTM) and Convolutional Neural Networks (CNNs). ARIMA models are frequently used in econometric analyses, providing a good benchmark for the problem under study. Our results indicate that ARIMA models and LSTM neural networks perform similarly for the forecasting task under consideration, while the combination of CNNs and LSTMs attains the best overall accuracy, but requires more time to be tuned. On the contrary, Prophet is quick and easy to use, but considerably less accurate.t overall accuracy, but requires more time to be tuned. On the contrary, Prophet is quick and easy to use, but considerably less accurate.