• Corpus ID: 51950905

A comparative study between LSTM and ARIMA for sales forecasting in retail

@inproceedings{Elmasdotter2018ACS,
  title={A comparative study between LSTM and ARIMA for sales forecasting in retail},
  author={Ajla Elmasdotter and Carl Nystr{\"o}mer},
  year={2018}
}
Food waste is a major environmental issue. Expired products are thrown away, implying that too much food is ordered compared to what is sold and that a more accurate prediction model is required wi ... 
kth.diva-portal.org
8 Citations
Highly Influential Citations
1
Background Citations
2
Results Citations
1

8 Citations

Demand forecasting at retail stage for selected vegetables: a performance analysis
Purpose The purpose of this study is to select the appropriate forecasting model at the retail stage for selected vegetables on the basis of performance analysis. Design/methodology/approach…
A comparative study of LSTM and ARIMA for energy load prediction with enhanced data preprocessing
TLDR
A new data preprocessing algorithm called STDAN (Same Time a Day Ago or Next) to fill the missing values of energy load prediction is proposed to improve the energy load forecasting accuracy.
Retail sales forecasting using LSTM and ARIMA-LSTM: A comparison with traditional econometric models and Artificial Neural Networks
Aggregate retail sales is an important economic indicator that requires precise understanding and forecasting. This research extends the study of Alon, Qi, and Sadowski (2001), which makes use of…
Retail Demand Forecasting with Artificial Neural Networks
  • Computer Science
  • 2020
TLDR
The main intention of this master thesis was to introduce a machine learning approach for a Retail Demand Forecasting problem and two LSTM models combined in a similar way as the Actor-Critic, outperforming the other models.
Time series forecasting of hospital Inpatients and Day case waiting list using ARIMA, TBATS and Neural Network Models
TLDR
The performance of ARIMA model found to be better in most of the case, where time series data has constant seasonal pattern, TBATS model is better where data having irregular seasonal pattern and AR-NN neural network model not great.
Review of ML and AutoML Solutions to Forecast Time-Series Data
TLDR
A review was conducted on the methods of analyzing time series starting from the traditional linear modeling techniques until the automated machine learning (AutoML) frameworks, including deep learning models.
A Review on the Comparison of Box-Jenkins ARIMA and LSTM of Deep Learning
TLDR
The outcomes of the overall discrepancy in error indicate that in regards of both RMSE and MAE, the LSTM-model tended to have greater predictive accuracy than the ARIMAmodel.
Bandwidth Provisioning for 4G Mobile Network Using Hybrid ARIMA-LSTM Based Traffic Forecasting

References

SHOWING 1-10 OF 26 REFERENCES
Application of Long Short-Term Memory Neural Network to Sales Forecasting in Retail—A Case Study
TLDR
A long short-term memory (LSTM) recurrent neural networks (RNN) network is tested on 45 weeks point of sale data of 66 products without considering the impact of seasonality and promotions, which validates the feasibility of the LSTM network to some degree.
Sales forecasting newspaper with ARIMA: A case study
TLDR
People are beginning to switch to using digital media for their daily activities, including changes in newspaper reading patterns to electronic news, according to research by the Pew Research Center.
Sales forecasting using extreme learning machine with applications in fashion retailing
A hybrid seasonal autoregressive integrated moving average and quantile regression for daily food sales forecasting
Research on sales forecasting based on ARIMA and BP neural network combined model
TLDR
The combined model proposed by this paper can be used in future prediction researches and industrial data analysis and is obviously enhanced, with an average error of forecast decreasing 10.4% by a large margin.
Long short-term memory neural network for air pollutant concentration predictions: Method development and evaluation.
ARIMA forecasting of primary energy demand by fuel in Turkey
An architecture for emergency event prediction using LSTM recurrent neural networks
Time‐series forecasting
TLDR
Chris Chatfield looks at the chequered history of forecasting and asks how to do it better using time-series data, and what statistical techniques and models might help us.
A novel neural network ensemble architecture for time series forecasting
...
...