Research on Fresh Produce Sales Prediction Algorithm for Store Based on Multidimensional Time Series Data Analysis

Zhiyu Li; Wei Yu; Wenwei Zhu; Haojie Wan; Jingjing Peng; Hui Wang

doi:10.4108/eetsis.3844

Authors

Zhiyu Li Wuhan University
Wei Yu Wuhan University
Wenwei Zhu Wuhan University
Haojie Wan Wuhan University
Jingjing Peng Wuhan University
Hui Wang Wuhan Branch of the National Science Library

DOI:

https://doi.org/10.4108/eetsis.3844

Keywords:

Fresh produce sales prediction, Multidimensional time series data, Combined prediction model, LSTM

Abstract

INTRODUCTION: Fresh produce is a daily necessity; however, offline stores often rely on personal experience for purchase, which is highly subjective and may result in inaccurate estimation of purchase quantities. This can lead to produce wastage and subsequently impact the profitability of business. This paper introduces a fresh produce sales prediction model, which can predict fresh produce sales by analyzing multidimensional time series data that influence sales. This model aims to provide guidance for fresh produce purchase in offline stores.

OBJECTIVES: The purpose of this study is to predict fresh produce sales by analyzing multidimensional time series data that influence sales. This aims to provide a basis for fresh produce purchase in stores, reduce produce wastage, and enhance business profitability.

METHODS: This paper proposes a fresh produce sales prediction model by analyzing multidimensional time series data that affect store sales of fresh produce. An essential component of this model is the ARIMA-LSTM combined prediction model. In this study, the weighted reciprocal of errors averaging method is selected as the weight determination method for the ARIMA-LSTM combined prediction model.

RESULTS: In this paper, the ARIMA-LSTM combined model is used for prediction in two scenarios: when the single-model prediction accuracy is superior and when it is inferior. Experimental results indicate that in the case of lower accuracy in single-model prediction, the combined prediction model outperforms, improving prediction accuracy by 3.86% as measured by MAPE. Comparative experiments are conducted between the fresh produce sales prediction model proposed in this paper and time series prediction framework Prophet, traditional LSTM model, and ARIMA model. The experimental results indicate that the proposed model outperforms the others.

CONCLUSION: The fresh produce sales prediction model proposed in this paper is based on multidimensional time series data to predict fresh produce sales in stores. This model can accurately predict the sales of fresh produce, providing purchase guidance for fresh produce stores, reducing fresh produce wastage caused by subjective purchasing factors, and increase business profits.

References

C.-H. W .Considering economic indicators and dynamic channel interactions to conduct sales forecasting for retail sectors[J].Computers & Industrial Engineering, 2022:165.

Zhou X, Zhai N, Li S, et al. Time series prediction method of industrial process with limited data based on transfer learning[J]. IEEE Transactions on Industrial Informatics, 2023,19 (5):6872-6882

Ren L, Jia Z, Laili Y, et al. Deep Learning for Time-Series Prediction in IIoT: Progress, Challenges, and Prospects[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023.

Bai Y T, Jia W, Jin X B, et al. Nonstationary Time Series Prediction Based on Deep Echo State Network Tuned by Bayesian Optimization[J]. Mathematics, 2023, 11(6): 1503.

Novianti Trisita and Utami Issa Dyah and Prima Dania Wike Agustin. Forecasting of salt demand using ARIMA model to prevent the bullwhip effect in salt supply chain[J]. Journal of Physics: Conference Series, 2022, 2193(1).

Longzhou Chen. Risk Analysis of Pork Market Price in China based on ARIMA Model[J]. Scientific Journal of Economics and Management Research, 2022, 4(2).

Zhao Xin. Forecast Port Container Throughput based on ARIMA Model[J]. Frontiers in Economics and Management, 2022, 3(2).

Arunraj N S, Ahrens D. A hybrid seasonal autoregressive integrated moving average and quantile regression for daily food sales forecasting[J]. International Journal of Production Economics, 2015, 170: 321-335.

Tofik Mussa Reshid. Ethiopian Economic Features and Changing Persistence: A Time Series Analysis. 2020, 9(3).

David Adugh Kuhe,Thomas Akwana Obed.An ARMA Model for Short-term Prediction of Hepatitis B Virus Seropositivity among Blood Donors in Lafia-nigeria. 2019 , : 1-11.

Prathap Rudra Boppuru, Ramesha K..Spatio-temporal Crime Analysis Using KDE and ARIMA Models in the Indian Context[J]. International Journal of Digital Crime and Forensics (IJDCF), 2020,12(4).

Ahmad T E et al. Fisheries forecasting, physical approach comparison between regression and autoregressive integrated moving average (ARIMA)[J]. IOP Conference Series: Earth and Environmental Science, 2022, 967(1).

Posch K, Truden C, Hungerländer P, et al. A Bayesian approach for predicting food and beverage sales in staff canteens and restaurants[J]. International Journal of Forecasting, 2022, 38(1): 321-338.

Hossain M S , Mahmood H . Short-term photovoltaic power forecasting using an LSTM neural network andsynthetic weather forecast[J].IEEE Access,2020,8:172524-172533.

Siami-namini S,Tavakoli N , Namin A S.A Comparison of ARIMA and LSTM in Forecasting Time Series[C]2018 17th IEEE International Conference on Machine Learning and Applications ( ICMLA ) IEEE , 2018:1394 -1901.

Lee W I, Chen C W, Chen K H, et al. A comparative study on the forecast of fresh food sales using logistic regression, moving average and BPNN methods[J]. Journal of Marine Science and Technology, 2012, 20(2): 4.

Absar Nurul et al. The efficacy of deep learning based LSTM model in forecasting the outbreak of contagious diseases[J]. Infectious Disease Modelling, 2021.

Shahani Niaz Muhammad et al. Predictive modeling of drilling rate index using machine learning approaches: LSTM, simple RNN, and RFA[J]. Petroleum Science and Technology, 2022, 40(5) : 534-555.

Pei Ying et al. Trend Prediction of DC Measuring System Based on LSTM[J]. Journal of Physics: Conference Series, 2021, 2083(3).

Wang L, Li X, Zhu H, et al. Influencing factors of livestream selling of fresh food based on a push-pull model: A two-stage approach combining structural equation modeling (SEM) and artificial neural network (ANN)[J]. Expert Systems with Applications, 2023, 212: 118799.

Bates J M, Granger C W J. The combination of forecasts[J].Journal of the Operational Research Society,1969,20(4):451-468.

Chandriah K K, Naraganahalli R V. RNN/LSTM with modified Adam optimizer in deep learning approach for automobile spare parts demand forecasting[J]. Multimedia Tools and Applications, 2021, 80(17): 26145-26159.

Guo Yan et al. Research on Precipitation Forecast Based on LSTM–CP Combined Model[J]. Sustainability, 2021, 13(21) : 11596-11596.

Luo T, Chang D, Xu Z. Research on Apparel Retail Sales Forecasting Based on xDeepFM-LSTM Combined Forecasting Model[J]. Information, 2022, 13(10): 497.

Wang S, Yang Y. M-GAN-XGBOOST model for sales prediction and precision marketing strategy making of each product in online stores[J]. Data Technologies and Applications, 2021, 55(5): 749-770.

Ahmed S, Chakrabortty R K, Essam D L, et al. Poly-linear regression with augmented long short term memory neural network: Predicting time series data[J]. Information Sciences, 2022, 606: 573-600.

Bekiroglu K, Gulay E, Duru O. A multi-method forecasting algorithm: Linear unbiased estimation of combine forecast[J]. Knowledge-Based Systems, 2022, 239: 107990.