Summary of Forecasting Automotive Supply Chain Shortfalls with Heterogeneous Time Series, by Bach Viet Do et al.
Forecasting Automotive Supply Chain Shortfalls with Heterogeneous Time Series
by Bach Viet Do, Xingyu Li, Chaoye Pan, Oleg Gusikhin
First submitted to arxiv on: 23 Jul 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a novel methodology to forecast first-tier supply chain disruptions in the automotive industry, utilizing features related to capacity, inventory, utilization, and processing. The authors construct a dataset consisting of many multivariate time series to identify and predict such disruptions early, which is crucial for maintaining seamless operations. The model integrates an enhanced Attention Sequence to Sequence Deep Learning architecture with Neural Network Embeddings to model group effects, and a Survival Analysis model. This model demonstrates strong performance in predicting operational disruptions, achieving 0.85 precision and 0.8 recall during the Quality Assurance phase across Ford’s five North American plants. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper helps companies like Ford predict when there might be problems with their supply chain, which is important because these issues can cause big financial losses. The authors created a huge dataset of time series data to forecast these disruptions and developed a new way to analyze this data using machine learning techniques. This method was tested on real-world data from Ford’s plants in North America and showed promising results. |
Keywords
* Artificial intelligence * Attention * Deep learning * Machine learning * Neural network * Precision * Recall * Time series
