Summary of Evaluating the Determinants Of Mode Choice Using Statistical and Machine Learning Techniques in the Indian Megacity Of Bengaluru, by Tanmay Ghosh and Nithin Nagaraj
Evaluating the Determinants of Mode Choice Using Statistical and Machine Learning Techniques in the Indian Megacity of Bengaluru
by Tanmay Ghosh, Nithin Nagaraj
First submitted to arxiv on: 25 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: General Economics (econ.GN)
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 presents a study that investigates mode choice decision making behavior for low-income households in Bengaluru using machine learning (ML) models. The authors compare the predictive performance of traditional discrete choice models with ML classifiers like decision trees, random forests, extreme gradient boosting, and support vector machines on a dataset of 1350 households. While the results show that ML models can be more accurate than statistical models, their black box nature poses significant interpretability challenges. To address this issue, the authors employ modern interpretability techniques like feature importance and individual conditional expectation plots to explain the decision making behavior using ML models. The study highlights the impact of travel costs on mode choice preferences, with a 10% increase in travel cost reducing the predicted probability of bus usage. In contrast, reducing travel time by 10% increases the preference for metro use. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study explores how machine learning (ML) models can be used to understand mode choice decisions made by low-income households in Bengaluru. The authors compare different ML algorithms and find that random forests performed best in terms of accuracy. To make these complex models more useful, they also explore ways to interpret the results, such as looking at which features are most important for each model’s predictions. Overall, this research can help improve our understanding of how people choose their transportation modes. |
Keywords
* Artificial intelligence * Extreme gradient boosting * Machine learning * Probability
