Author(s)

Feng Wang ¹, Joey Aviles ¹

Affiliation(s)

¹ Graduate School, Angeles University Foundation, 2009 Angeles City, Philippines

Corresponding Author

Joey Aviles

ABSTRACT

The objective of this study was to explore the combined use of time series and neural networks, employing the Narxnet algorithm, for predicting commodity sales volume. The Narxnet algorithm is a neural network model specifically designed for handling time series data, allowing for the utilization of historical data and external factors to forecast future sales volume. By harnessing the strengths of time series analysis and neural networks, we aimed to achieve more accurate predictions of commodity sales volume and assist businesses in formulating more effective supply chain management and marketing strategies. In this study, we investigated the performance of the Narxnet algorithm in predicting commodity sales volume, analyzing its predictive accuracy, model complexity, data requirements, and its adaptability to trends and seasonality. The obtained optimal performance was 85%, which, although lower than 90%, was attributed to the limited sample size. It is believed that a larger sample size would significantly enhance the algorithm's performance. This research provides insights into the field of commodity sales volume prediction, offering a perspective on the potential use of multiple algorithmic approaches to improve performance.

KEYWORDS

Time series, neutral network, machine learning, sales, algorithm

CITE THIS PAPER

Feng Wang, Joey Aviles, Research on Synergistic Enhancement of Sales Forecasting through Time Series and Neural Networks. Information Systems and Economics (2023) Vol. 4: 53-61. DOI: http://dx.doi.org/10.23977/infse.2023.040406.

REFERENCES

[1] Raubitzek S, Neubauer T. Taming the Chaos in Neural Network Time Series Predictions [J]. Entropy, 2021, 23(11): 1424.
[2] Ali M, Khan D M, Aamir M, et al. Predicting the Direction Movement of Financial Time Series Using Artificial Neural Network and Support Vector Machine [J]. Complexity, 2021: 1–13.
[3] Bento P M R, Pombo J A N, Calado M R A, et al. Stacking Ensemble Methodology Using Deep Learning and ARIMA Models for Short-Term Load Forecasting [J]. Energies, 2021, 14(21): 7378.
[4] Li C, Fang X, Yan Z, et al. Research on Gas Concentration Prediction Based on the ARIMA-LSTM Combination Model [J]. Processes, 2023, 11(1): 174.
[5] Li M, Ji S, Liu G. Forecasting of Chinese E-Commerce Sales: An Empirical Comparison of ARIMA, Nonlinear Autoregressive Neural Network, and a Combined ARIMA-NARNN Model [J]. Mathematical Problems in Engineering, 2018: 1–12.
[6] Zain Z M, Alturki N M. COVID-19 Pandemic Forecasting Using CNN-LSTM: A Hybrid Approach [J]. Journal of Control Science and Engineering, 2021: 1–23.
[7] Wang J. Analysis of Sports Performance Prediction Model Based on GA-BP Neural Network Algorithm [J]. Computational Intelligence and Neuroscience, 2021: 1–12.
[8] Yang Z, Mehmed E E. Artificial neural networks in freight rate Forecasting [J]. Maritime Economics & Logistics, 2019, 21(3): 390–414.

Sponsors, Associates, and Links

---

• Accounting, Auditing and Finance
  
  
• Industrial Engineering and Innovation Management
  
  
• Tourism Management and Technology Economy
  
  
• Journal of Computational and Financial Econometrics
  
  
• Financial Engineering and Risk Management
  
  
• Accounting and Corporate Management
  
  
• Social Security and Administration Management
  
  
• Population, Resources & Environmental Economics
  
  
• Statistics & Quantitative Economics
  
  
• Agricultural & Forestry Economics and Management
  
  
• Social Medicine and Health Management
  
  
• Land Resource Management
  
  
• Information, Library and Archival Science
  
  
• Journal of Human Resource Development
  
  
• Manufacturing and Service Operations Management
  
  
• Operational Research and Cybernetics