A Hybrid Extreme Learning Machine Model with Harris Hawks Optimisation Algorithm: An Optimised Model for Product Demand Forecasting Applications

Journal article


Chaudhuri, K. D. and Alkan, B. (2022). A Hybrid Extreme Learning Machine Model with Harris Hawks Optimisation Algorithm: An Optimised Model for Product Demand Forecasting Applications. Applied Intelligence. https://doi.org/10.1007/s10489-022-03251-7
AuthorsChaudhuri, K. D. and Alkan, B.
Abstract

Accurate and real-time product demand forecasting is the need of the hour in the world of supply chain management. Predicting future product demand from historical sales data is a highly non-linear problem, subject to various external and environmental factors. In this work, we propose an optimised forecasting model – an extreme learning machine (ELM) model coupled with the Harris Hawks optimisation (HHO) algorithm to forecast product demand in an e-commerce company. ELM is preferred over traditional neural networks mainly due to its fast computational speed, which allows efficient demand forecasting in real-time. Our ELM-HHO model performed significantly better than ARIMA models that are commonly used in industries to forecast product demand. The performance of the proposed ELM-HHO model was also compared with traditional ELM, ELM auto-tuned using Bayesian Optimisation (ELM-BO), Gated Recurrent Unit (GRU) based recurrent neural network and Long Short Term Memory (LSTM) recurrent neural network models. Different performance metrics, i.e., Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Percentage Error (MPE) were used for the comparison of the selected models. Horizon forecasting at 3 days and 7 days ahead was also performed using the proposed approach. The results revealed that the proposed approach is superior to traditional product demand forecasting models in terms of prediction accuracy and it can be applied in real-time to predict future product demand based on the previous week’s sales data. In particular, considering RMSE of forecasting, the proposed ELM-HHO model performed 62.73% better than the statistical ARIMA(7,1,0) model, 40.73% better than the neural network based GRU model, 34.05% better than the neural network based LSTM model, 27.16% better than the traditional non-optimised ELM model with 100 hidden nodes and 11.63% better than the ELM-BO model in forecasting product demand for future 3 months. The novelty of the proposed approach lies in the way the fast computational speed of ELMs has been combined with the accuracy gained by tuning hyperparameters using HHO. An increased number of hyperparameters has been optimised in our methodology compared to available models. The majority of approaches to improve the accuracy of ELM so far have only focused on tuning the weights and the biases of the hidden layer. In our hybrid model, we tune the number of hidden nodes, the number of input time lags and even the type of activation function used in the hidden layer in addition to tuning the weights and the biases. This has resulted in a significant increase in accuracy over previous methods. Our work presents an original way of performing product demand forecasting in real-time in industry with highly accurate results which are much better than pre-existing demand forecasting models.

KeywordsDemand Forecasting, Supply Chain Management, Extreme Learning Machines, Artificial Neural Networks, Optimisation, Harris Hawks Optimisation, Hyperparameter tuning, ARIMA
Year2022
JournalApplied Intelligence
PublisherSpringer
ISSN1573-7497
Digital Object Identifier (DOI)https://doi.org/10.1007/s10489-022-03251-7
Publication dates
Print26 Jan 2022
Publication process dates
Accepted15 Jan 2022
Deposited17 Jan 2022
Publisher's version
License
File Access Level
Open
Accepted author manuscript
License
File Access Level
Controlled
Permalink -

https://openresearch.lsbu.ac.uk/item/8z0zq

Download files


Publisher's version
  • 58
    total views
  • 49
    total downloads
  • 3
    views this month
  • 4
    downloads this month

Export as

Related outputs

An End-to-End Big Data Analytics Platform for IoT-enabled Smart Factories: A Case Study of Battery Module Assembly System for Electric Vehicles
Kahveci, S., Alkan, B., Ahmad, M. and Harrison, R. (2022). An End-to-End Big Data Analytics Platform for IoT-enabled Smart Factories: A Case Study of Battery Module Assembly System for Electric Vehicles. Journal of Manufacturing Systems. 63, pp. 214-223. https://doi.org/10.1016/j.jmsy.2022.03.010
Performance Comparison of Recent Population-based Metaheuristic Optimisation Algorithms in Mechanical Design Problems of Machinery Components
Alkan, B. and Chinnathai, M.K. (2021). Performance Comparison of Recent Population-based Metaheuristic Optimisation Algorithms in Mechanical Design Problems of Machinery Components. MDPI Machines. 9 (12), p. 341.
A novel data-driven approach to support decision-making during production scale-up of assembly systems
Alkan, B. (2021). A novel data-driven approach to support decision-making during production scale-up of assembly systems. Journal of Manufacturing Systems. 59, pp. 577-595. https://doi.org/10.1016/j.jmsy.2021.03.018
Identifying Optimal Granularity Level of Modular Assembly Supply Chains Based on Complexity-Modularity Trade-Off
Alkan, B., Bullock, S. and Galvin, K. (2021). Identifying Optimal Granularity Level of Modular Assembly Supply Chains Based on Complexity-Modularity Trade-Off. IEEE Access. 9, pp. 57907 - 57921. https://doi.org/10.1109/ACCESS.2021.3072955
Assessing operational complexity of manufacturing systems based on algorithmic complexity of key performance indicator time-series
Alkan, B. and Bullock, S. (2020). Assessing operational complexity of manufacturing systems based on algorithmic complexity of key performance indicator time-series. Journal of the Operational Research Society. https://doi.org/10.1080/01605682.2020.1779622
A Design Process Framework to Deal with Non-functional Requirements in Conceptual System Designs
Alkan, B., Seth, B., Galvin, K. and Johnson, A. (2020). A Design Process Framework to Deal with Non-functional Requirements in Conceptual System Designs. Complex Systems Design & Management. Paris 15 - 17 Dec 2020
Improving just-in-time delivery performance of IoT-enabled flexible manufacturing systems with AGV based material transportation
Yao, F, Alkan, B, Ahmad, B and Harrison, R (2020). Improving just-in-time delivery performance of IoT-enabled flexible manufacturing systems with AGV based material transportation. Sensors (Switzerland). 20 (21), pp. 1-25. https://doi.org/10.3390/s20216333
A framework to predict energy related key performance indicators of manufacturing systems at early design phase
Assad, F, Alkan, B, Chinnathai, MK, Ahmad, MH, Rushforth, EJ and Harrison, R (2019). A framework to predict energy related key performance indicators of manufacturing systems at early design phase. Procedia CIRP. 81, pp. 145-150. https://doi.org/10.1016/j.procir.2019.03.026
A Framework for Pilot Line Scale-up using Digital Manufacturing
Chinnathai, M. K., Al-Mowafy, Z., Alkan, B., Vera, D. and Harrison, R. (2019). A Framework for Pilot Line Scale-up using Digital Manufacturing. Procedia CIRP. 81, pp. 962-967. https://doi.org/10.1016/j.procir.2019.03.235
An experimental investigation on the relationship between perceived assembly complexity and product design complexity
Alkan, B. (2019). An experimental investigation on the relationship between perceived assembly complexity and product design complexity. International Journal on Interactive Design and Manufacturing (IJIDeM). 13 (3), pp. 1145-1157. https://doi.org/10.1007/s12008-019-00556-9
A virtual engineering based approach to verify structural complexity of component-based automation systems in early design phase
Alkan, B. and Harrison, R. (2019). A virtual engineering based approach to verify structural complexity of component-based automation systems in early design phase. Journal of Manufacturing Systems. 53, pp. 18-31. https://doi.org/10.1016/j.jmsy.2019.09.001
Pilot To Full-Scale Production: A Battery Module Assembly Case Study
Chinnathai, M.K., Alkan, B., Vera, D. and Harrison, R. (2018). Pilot To Full-Scale Production: A Battery Module Assembly Case Study. Procedia CIRP. 72, pp. 796-801. https://doi.org/10.1016/j.procir.2018.03.194
Proposing a Holistic Framework for the Assessment and Management of Manufacturing Complexity through Data-centric and Human-centric Approaches
Alkan, B. (2018). Proposing a Holistic Framework for the Assessment and Management of Manufacturing Complexity through Data-centric and Human-centric Approaches. Proceedings of the 3rd International Conference on Complexity, Future Information Systems and Risk (COMPLEXIS 2018).
Complexity in manufacturing systems and its measures: a literature review
Alkan, B., Vera, D., Ahmad, M., Ahmad, B. and Harrison, R. (2018). Complexity in manufacturing systems and its measures: a literature review. European Journal of Industrial Engineering . 12 (1). https://doi.org/10.1504/EJIE.2018.089883
Convertibility Evaluation of Automated Assembly System Designs for High Variety Production
Chinnathai, M.K., Alkan, B. and Harrison, R. (2017). Convertibility Evaluation of Automated Assembly System Designs for High Variety Production. Elsevier BV. https://doi.org/10.1016/j.procir.2017.01.005
Assessing Complexity of Component-Based Control Architectures Used in Modular Automation Systems
Alkan, B., Vera, D., Chinnathai, M. K. and Harrison, R. (2017). Assessing Complexity of Component-Based Control Architectures Used in Modular Automation Systems . International Journal of Computer and Electrical Engineering . 9 (1). https://doi.org/10.17706/ijcee.2017.9.1.393-402
A method to assess assembly complexity of industrial products in early design phase
Alkan, B., Vera, D., Ahmad, B. and Harrison, R. (2017). A method to assess assembly complexity of industrial products in early design phase. IEEE Access. 6, pp. 989-999. https://doi.org/10.1109/ACCESS.2017.2777406
A Framework for Automatically Realizing Assembly Sequence Changes in a Virtual Manufacturing Environment
Ahmad, M, Ahmad, B, Harrison, R, Alkan, B, Vera, D, Meredith, J and Bindel, A (2016). A Framework for Automatically Realizing Assembly Sequence Changes in a Virtual Manufacturing Environment. Elsevier BV. https://doi.org/10.1016/j.procir.2016.04.178
A Lightweight Approach for Human Factor Assessment in Virtual Assembly Designs: An Evaluation Model for Postural Risk and Metabolic Workload
Alkan, B, Vera, D, Ahmad, M, Ahmad, B and Harrison, R (2016). A Lightweight Approach for Human Factor Assessment in Virtual Assembly Designs: An Evaluation Model for Postural Risk and Metabolic Workload. Elsevier BV. https://doi.org/10.1016/j.procir.2016.02.115
A Model for Complexity Assessment in Manual Assembly Operations Through Predetermined Motion Time Systems
Alkan, B, Vera, D, Ahmad, M, Ahmad, B and Harrison, R (2016). A Model for Complexity Assessment in Manual Assembly Operations Through Predetermined Motion Time Systems. Procedia CIRP. 44, pp. 429-434. https://doi.org/10.1016/j.procir.2016.02.111
Hydrogen Fuel Cell Pick and Place Assembly Systems: Heuristic Evaluation of Reconfigurability and Suitability
Ahmad, M., Ahmad, B., Alkan, B., Vera, D., Harrison, R., Meredith, J. and Bindel, A. (2016). Hydrogen Fuel Cell Pick and Place Assembly Systems: Heuristic Evaluation of Reconfigurability and Suitability. Procedia CIRP. 57, pp. 428-433. https://doi.org/10.1016/j.procir.2016.11.074
The Use of a Complexity Model to Facilitate in the Selection of a Fuel Cell Assembly Sequence
Ahmad, M., Alkan, B., Ahman, B., Vera, D., Harrison, R., Meredith, J. and Bindel, A. (2016). The Use of a Complexity Model to Facilitate in the Selection of a Fuel Cell Assembly Sequence. Procedia CIRP. 44, pp. 169-174. https://doi.org/10.1016/j.procir.2016.02.054
Design Evaluation of Automated Manufacturing Processes Based on Complexity of Control Logic
Alkan, B., Vera, D., Ahmad, M., Ahmad, B. and Harrison, R. (2016). Design Evaluation of Automated Manufacturing Processes Based on Complexity of Control Logic. Procedia CIRP. 50, pp. 141-146. https://doi.org/10.1016/j.procir.2016.05.031