Lessons Learned Applying Deep Learning Approaches to Forecasting Complex Seasonal Behavior

TL;DR

This paper evaluates the effectiveness of various deep learning recurrent neural networks in forecasting complex, seasonal call center data, providing practical insights into their optimization and comparative performance.

Contribution

It offers a comprehensive analysis of RNN models like Elman, LSTM, and GRU for seasonal forecasting and compares them with traditional methods using real-world data.

Findings

RNNs can effectively model complex seasonal patterns.

Optimized RNN configurations outperform classical methods in validation error.

Practical guidelines for tuning deep learning models in forecasting tasks.

Abstract

Deep learning methods have gained popularity in recent years through the media and the relative ease of implementation through open source packages such as Keras. We investigate the applicability of popular recurrent neural networks in forecasting call center volumes at a large financial services company. These series are highly complex with seasonal patterns - between hours of the day, day of the week, and time of the year - in addition to autocorrelation between individual observations. Though we investigate the financial services industry, the recommendations for modeling cyclical nonlinear behavior generalize across all sectors. We explore the optimization of parameter settings and convergence criteria for Elman (simple), Long Short-Term Memory (LTSM), and Gated Recurrent Unit (GRU) RNNs from a practical point of view. A designed experiment using actual call center data across many different "skills" (income call streams) compares performance measured by validation error rates of the best observed RNN configurations against other modern and classical forecasting techniques. We summarize the utility of and considerations required for using deep learning methods in forecasting.