Forecasting Weakly Correlated Time Series in Tasks of Electronic Commerce

TL;DR

This paper compares exponential smoothing, neural networks, and decision trees for forecasting weakly correlated conversion rate time series in electronic commerce, analyzing their strengths and weaknesses.

Contribution

It provides a comparative analysis of different forecasting methods applied to weakly correlated e-commerce time series, highlighting their advantages and disadvantages.

Findings

Neural networks showed higher accuracy in some cases.

Exponential smoothing was more computationally efficient.

Decision trees provided interpretable models.

Abstract

Forecasting of weakly correlated time series of conversion rate by methods of exponential smoothing, neural network and decision tree on the example of conversion percent series for an electronic store is considered in the paper. The advantages and disadvantages of each method are considered.