AI-Augmented Fleet Intelligence in a GPS-Based Mobility SaaS: Predictive Fare Modeling, Demand Forecasting, and Driver Performance Scoring in Digikab
DOI:
https://doi.org/10.30871/jaic.v10i4.13000Keywords:
Fleet Intelligence, Demand Forecasting, Driver Performance Scoring, Dynamic Fare Modeling, Mobility SaaS, Gradient-Boosted Trees, GPS Telematics, Large Language Models, Demand Elasticity, Cold-Start ProblemAbstract
Small taxi fleet operators operating in emerging markets generate rich GPS telemetry through every completed trip, yet that data is rarely fed back into operational decisions. This study evaluates three AI-augmented capabilities, demand forecasting, predictive fare modeling, and driver performance scoring, deployed within Digikab, a SaaS platform built on GPS-enabled Android devices, across 47 independent fleet operators managing 284 vehicles over a six-month observation window. Using a quasi-experimental design with 29 AI-enabled operators and 18 controls on the same platform, this study applies gradient-boosted tree models (XGBoost/LightGBM) for zone-level demand forecasting, achieving a mean absolute error (MAE) of 2.14 trips per zone per hour (RMSE = 3.87, R² = 0.81) against held-out validation data. Demand elasticity estimation for fare optimization is formalized through an arc elasticity framework applied to operator-specific tariff history. Driver performance is decomposed into five weighted behavioral dimensions derived exclusively from the existing trip record, with coaching feedback generated via a large language model (LLM). Operators in the AI-enabled cohort demonstrated a 14.3% improvement in revenue per driver-hour (p = 0.003), a 22.4% reduction in idle time proportion (p = 0.007), an 8.9 percentage-point increase in trip completion rate (p = 0.014), and a 19.0% reduction in average passenger wait time (p = 0.012). The cold-start challenge for new operators is addressed through a progressive blending architecture that phases per-operator training signal in over a minimum three-month accumulation period. Findings demonstrate that meaningful predictive fleet intelligence is achievable at trip-history volumes in the thousands rather than millions, provided model architecture, output design, and operator interface are co-designed for the small-fleet context.
Downloads
References
[1] Shafiq Alam, et al., "A comparative study of machine learning models for taxi-demand prediction using a big data framework," Public Transport, 2025. [Online]. Available: https://link.springer.com/article/10.1007/s12469-025-00401-1
[2] Suryakant Kaushik, "Driving Innovation in Fleet Management: An Integrated Data-Driven Framework for Operational Excellence and Sustainability," In Proceedings of the 14th International Conference on Data Science, Technology and Applications, 2025. [Online]. Available: https://www.scitepress.org/PublishedPapers/2025/135614/
[3] Jintao Ke, et al., "Short-term forecasting of passenger demand under on-demand ride services: A spatio-temporal deep learning approach," Transportation Research Part C: Emerging Technologies, 2017. [Online]. Available: https://www.sciencedirect.com/science/article/abs/pii/S0968090X17302899
[4] Wang, Jiyang, et al., "A Survey on Driver Behavior Analysis From In-Vehicle Cameras," IEEE Transactions on Intelligent Transportation Systems, 2022. [Online]. Available: https://ieeexplore.ieee.org/document/9618784
[5] Jiaru Bai, et al., "Hiding in plain sight: Surge pricing and strategic providers," Production and Operations Management, 2023. [Online]. Available: https://onlinelibrary.wiley.com/doi/epdf/10.1111/poms.14064
[6] P. Sudheer Benarji, et al., "Taxi Demand Prediction using Machine Learning," International Research Journal of Engineering and Technology (IRJET), 2023. [Online]. Available: https://www.irjet.net/archives/V10/i5/IRJET-V10I5234.pdf
[7] Suryakant Kaushik, et al., "AI-Driven Decision Support in Fleet Management: Creating Value Through Optimization and Innovation," IGI Global Scientific Publishing, 2026. [Online]. Available: https://www.igi-global.com/chapter/ai-driven-decision-support-in-fleet-management/393974
[8] Alejandro Barredo Arrieta, et al., "Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities, and challenges toward responsible AI," ACM Digital Library, 2020. [Online]. Available: https://dl.acm.org/doi/10.1016/j.inffus.2019.12.012
[9] Panteli Antiopi and Basilis Boutsinas, "Addressing the Cold-Start Problem in Recommender Systems Based on Frequent Patterns," ResearchGate, 2023. [Online]. Available: https://www.researchgate.net/publication/369560430
[10] Yu Zheng, et al., "Urban Computing: Concepts, Methodologies, and Applications," ACM Transactions on Intelligent Systems and Technology (TIST), 2014. [Online]. Available: https://dl.acm.org/doi/10.1145/2629592
[11] OECD discussion paper for the G7, "AI adoption by small and medium‑sized enterprises," 2025. [Online]. Available: https://www.oecd.org/content/dam/oecd/en/publications/reports/2025/12/ai-adoption-by-small-and-medium-sized-enterprises_9c48eae6/426399c1-en.pdf
[12] Tianqi Chen and Carlos Guestrin, "XGBoost: A Scalable Tree Boosting System," arXiv, 2016. [Online]. Available: https://arxiv.org/pdf/1603.02754
[13] Huaxiu Yao, et al., "Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction," arXiv, 2018. [Online]. Available: https://arxiv.org/pdf/1803.01254
[14] Rui Chen, et al., "Autonomous fleet management system in smart ports: Practical design and analytical considerations," Multimodal Transportation, 2025. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2772586325000255
[15] Harish Guda and Upender Subramanian, "Your Uber Is Arriving: Managing On-Demand Workers Through Surge Pricing, Forecast Communication, and Worker Incentives," Management Science, 2019. [Online]. Available: https://pubsonline.informs.org/doi/epdf/10.1287/mnsc.2018.3050
[16] Research and Market, "Fleet Telematics Market by Vehicle Type, Package Type, Vendor Type, Solution Type, and Region, Global Forecast to 2032, Product Image Fleet Telematics Market by Vehicle Type, Package Type, Vendor Type, Solution Type, and Region, Global Forecast to 2032," 2026. [Online]. Available: https://www.researchandmarkets.com/report/commercial-vehicle-telematics?srsltid=AfmBOopN6BYkgq7RlXhhhknGsZNku4BMFQjbXTyVc2Dzzj1WV53amRnJ
[17] Hickman, Jeffrey S., "Self-Management for Safety: Impact of Self-Monitoring versus Objective Feedback," Virginia Tech, 2025. [Online]. Available: https://vtechworks.lib.vt.edu/items/12d82e59-08a2-448a-81fa-772f234940cd
[18] Iman Rahimi, "Large Language Models in Decision Support Systems for Operations Research: Domain-Focused Perspectives," ResearchGate, 2026. [Online]. Available: https://www.researchgate.net/publication/400235283
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Jai Chandra Mouli Langoju
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
