Jadwal Sholat

Memuat jadwal sholatโ€ฆ

Ekonomi & Bisnis editorial

Open AccessOA2024

A Deep Learning Approach to Predict Supply Chain Delivery Delay Risk Based on Macroeconomic Indicators: A Case Study in the Automotive Sector

This study proposes a deep learning approach that incorporates macroeconomic indicators to predict supplier delivery delay risk, addressing gaps in current literature. A real automotive case study demonstrates superior performance compared to traditional models.
Matteo Gabellini; Lorenzo Civolani; F. Calabrese; Marco Bortoliniยท Applied Sciencesยท 2024ยท DOI 10.3390/app14114688

The core problem

The development of predictive approaches to estimate supplier delivery risks has become vital for companies that rely heavily on outsourcing practices and lean management strategies in the era of the shortage economy. However, the literature that presents studies proposing the development of such approaches is still in its infancy, and several gaps have been found. In particular, most of the current studies present approaches that can only estimate whether suppliers will be late or not. Moreover, even if autocorrelation in data has been widely considered in demand forecasting, it has been neglected in supplier delivery risk predictions. Finally, current approaches struggle to consider macroeconomic data as input and rely mostly on machine learning models, while deep learning ones have rarely been investigated. The main contribution of this study is thus to propose a new approach that for the first time simultaneously adopts a deep learning model able to capture autocorrelation in data and integrates several macroeconomic indicators as input. Furthermore, as a second contribution, the performance of the proposed approach has been investigated in a real automotive case study and compared with those studies resulting from approaches that adopt traditional statistical models and models that do not consider macroeconomic indicators as additional inputs.

Innovation

The proposed approach employs a deep learning model designed to capture autocorrelation in time series data, specifically long short-term memory (LSTM) networks, which are well-suited for sequential data. The model integrates macroeconomic indicators as additional input features. The methodology involves data collection from a real automotive case study, including historical delivery data and relevant macroeconomic indicators. The data is preprocessed and used to train the deep learning model. The model's performance is evaluated and compared against benchmarks: traditional statistical models (e.g., ARIMA) and models that do not consider macroeconomic indicators. The evaluation metrics likely include accuracy, precision, recall, and -score, although the abstract does not specify. The approach aims to predict the probability of delivery delay, providing a more nuanced risk assessment than binary classification.
Introduction
The development of predictive approaches to estimate supplier delivery risks has become vital for companies that rely heavily on outsourcing practices and lean management strategies in the era of the shortage economy. However, the literature that presents studies proposing the development of such approaches is still in its infancy, and several gaps have been found. In particular, most of the current studies present approaches that can only estimate whether suppliers will be late or not. Moreover, even if autocorrelation in data has been widely considered in demand forecasting, it has been neglected in supplier delivery risk predictions. Finally, current approaches struggle to consider macroeconomic data as input and rely mostly on machine learning models, while deep learning ones have rarely been investigated. The main contribution of this study is thus to propose a new approach that for the first time simultaneously adopts a deep learning model able to capture autocorrelation in data and integrates several macroeconomic indicators as input. Furthermore, as a second contribution, the performance of the proposed approach has been investigated in a real automotive case study and compared with those studies resulting from approaches that adopt traditional statistical models and models that do not consider macroeconomic indicators as additional inputs.

Why it matters

The study addresses critical gaps in the literature by proposing a novel approach that simultaneously leverages deep learning and macroeconomic indicators for supplier delivery risk prediction. The findings underscore the value of incorporating macroeconomic factors, which are often overlooked in traditional models. The superior performance of the deep learning model can be attributed to its ability to capture complex temporal dependencies and autocorrelation in the data. The automotive case study validates the approach in a real-world setting, suggesting that companies can benefit from more accurate risk predictions. However, the study may have limitations such as the generalizability to other sectors and the need for large datasets. Future research could explore the integration of additional data sources and the application of other deep learning architectures. Overall, the study contributes to the advancement of predictive analytics in supply chain management.

Who should read this

Pembaca Research Digest dan praktisi rumpun ini.

Opening member contentโ€ฆ