Sales forecasting using multivariate long short term memory network models

Abstract

In the retail domain, estimating the sales before actual sales become known plays a key role in maintaining a successful business. This is due to the fact that most crucial decisions are bound to be based on these forecasts. Statistical sales forecasting models like ARIMA (Auto-Regressive Integrated Moving Average), can be identified as one of the most traditional and commonly used forecasting methodologies. Even though these models are capable of producing satisfactory forecasts for linear time series data they are not suitable for analyzing non-linear data. Therefore, machine learning models (such as Random Forest Regression, XGBoost) have been employed frequently as they were able to achieve better results using non-linear data. The recent research shows that deep learning models (e.g. recurrent neural networks) can provide higher accuracy in predictions compared to machine learning models due to their ability to persist information and identify temporal relationships. In this paper, we adopt a special variant of Long Short Term Memory (LSTM) network called LSTM model with peephole connections for sales prediction. We first build our model using historical features for sales forecasting. We compare the results of this initial LSTM model with multiple machine learning models, namely, the Extreme Gradient Boosting model (XGB) and Random Forest Regressor model(RFR). We further improve the prediction accuracy of the initial model by incorporating features that describe the future that is known to us in the current moment, an approach that has not been explored in previous state-of-the-art LSTM based forecasting models. The initial LSTM model we develop outperforms the machine learning models achieving 12% - 14% improvement whereas the improved LSTM model achieves 11\% - 13\% improvement compared to the improved machine learning models. Furthermore, we also show that our improved LSTM model can obtain a 20% - 21% improvement compared to the initial LSTM model, achieving significant improvement.

Machine Learning Based Restaurant Sales Forecasting

“…Although some skepticism has been seen towards neural network methods, recurrent networks are showing improvements over ARIMA and other notable statistical methods. Especially when considering the now popular recurrent LSTM model, we see improvements when comparing to ARIMA models [8,9], although the works do not compare the results with a larger subset of machine learning methods. Researchers have recently begun improving the accuracy of deep learning forecasts over larger multi-horizon windows and are also beginning to incorporate hybrid deep learning-ARMIA models [7].…”

“…Both architectures are specific cases [12] or otherwise modified from the base RNN model by the addition of gating units in the recurrent layers. Some studies have been completed, suggesting that LSTMs significantly improve retail sales forecasting [9].…”

“…In the modern landscape, neural networks and other machine learning methods have been suggested as powerful alternatives to traditional statistical analysis [5][6][7][8][9]. There are hundreds [10] of new methods and models being surveyed and tested, many of which are deep learning neural networks, and progress is being seen in image classification, language processing, and reinforcement learning [5].…”

An Improved Equilibrium Optimizer Algorithm and Its Application in LSTM Neural Network

“…The results revealed its possible applicability in various cryptocurrencies prediction [34]. Helmini and Jihan adopted a special variant LSTM with peephole connections for the sales forecasting tasks, proved that the initial LSTM and improved LSTM both outperform two machine learning models (extreme gradient boosting (XGB) and random forest regressor (RFR)) [35]. To enhance the performance of the LSTM model, Gers and Schmidhuber proposed a novel adaptive "forget gate" that enables an LSTM cell to learn to reset itself at appropriate times [36], Karim and Majumdar added the attention model to detect regions of the input sequence that contribute to the class label through the context vector [37].…”

Demand Forecasting of Individual Probability Density Functions with Machine Learning

“…Both concepts, LSTM cells and self-attention, aim at learning the elements of the individual time series from the data that are deemed important for the prediction of the future values by the algorithm. The interest in deep learning approaches for demand forecasting has increased significantly recently, see, e.g., [38][39][40][41][42]. A review of deep learning methods for time series forecasting in a wide range of applications can also be found in [43], and the use of RNNs with focus on industrial applications is discussed in [44].…”