Laya K Shajan, Madhan Senthilkumar, Harshitha Reddy Muramreddy, Pallavi Jakkula, and Sai Inapakolla

DOI: https://doi.org/10.5281/zenodo.23140801

Ride-hailing apps are built mainly to book a ride, match a driver and reach the destination quickly. Safety and accessibility are usually added afterwards as a separate SOS button or a support-ticket system, so women, elderly riders and persons with disabilities (PWD) are often poorly served. This paper presents SafeGo, a ride-hailing platform that brings passenger-specific ride modes, machine-learning-based safety-risk prediction, accessibility-aware driver matching, PIN-based ride verification, live monitoring, SOS emergency response, transparent fare calculation and an administrative command center into one system. SafeGo provides four ride modes (Normal, Pink, Elderly and PWD), and a Random Forest classifier uses temporal, geographical, trip-level and mode-related features to place each trip in the Stable, Cautious or High Priority category. On a held-out synthetic test set of 2,000 samples the classifier achieved 99.80% accuracy, 99.87% macro precision, 99.78% macro recall and 99.82% macro F1-score, with a mean prediction time of 32.27 ms. Scenario-based tests show that predictions change with the ride mode and trip context. Because the dataset is synthetic, these figures describe model behaviour on the evaluation data and are not a claim about real-world accuracy

—SafeGo, Ride-Hailing, Passenger Safety, Random Forest, Risk Prediction, PWD Accessibility, Driver Matching, PIN Verification, SOS Emergency Response, Intelligent Transportation.

This paper presented SafeGo, a ride-hailing platform that brings transportation, passenger safety, accessibility and emergency response into one connected system. Beyond basic A-to-B booking, it adds four ride modes, mode-aware driver matching, PIN-based verification, live monitoring, SOS response, dynamic fare calculation and centralised administration. On a held-out synthetic set of 2,000 samples, the Random Forest safety-risk classifier reached 99.80% accuracy and 99.82% macro F1 with a mean prediction time of 32.27 ms, and scenario tests showed that its output shifts with ride mode and context. The next step is testing against real-world data and field conditions

[1] R. Sharma et al., “IoT-Based Women Safety Device with GPS Tracking and Emergency Alerts,” IEEE Access, 2021.
[2] S. Gupta et al., “Mobile-Based Emergency Alert System Using GPS and GSM,” International Journal of Engineering Research, 2020.
[3] A. Verma et al., “Smart Ride Booking System with Real-Time Tracking and Safety Features,” Springer Conference Proceedings, 2022.
[4] P. Nair et al., “Machine Learning-Based Risk Prediction in Smart Transportation Systems,” Elsevier Journal, 2022.
[5] K. Patel et al., “Accessibility Solutions for Persons with Disabilities in Transportation Systems,” Journal of Transport & Health, 2021.
[6] D. Roy et al., “AI-Based Driver Behaviour Analysis for Safe Transportation,” IEEE Smart Cities Conference, 2023.
[7] M. Khan et al., “Real-Time Location Tracking System Using GPS and IoT,” International Journal of Computer Applications, 2020.
[8] S. Iyer et al., “Emergency Response Optimization Using Mobile Applications,” IEEE Conference Publications, 2021.
[9] J. Singh et al., “Cloud-Based Smart Mobility Platforms for Urban Transport,” IEEE Access, 2022.
[10] L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, Oct. 2001.
[11] M. Sokolova and G. Lapalme, “A systematic analysis of performance measures for classification tasks,” Information Processing & Management, vol. 45, no. 4, pp. 427–437, Jul. 2009.
[12] Y. Ge, C. R. Knittel, D. MacKenzie, and S. Zoepf, “Racial and gender discrimination in transportation network companies,” NBER Working Paper No. 22776, Oct. 2016.
[13] J. Bezyak, B. Sabella, and R. Gattis, “Public transportation: An investigation of barriers for people with disabilities,” Journal of Disability Policy Studies, vol. 28, no. 1, pp. 52–60, 2017.
[14] A. Loukaitou-Sideris, “Fear and safety in transit environments from the women’s perspective,” Security Journal, vol. 27, no. 2, pp. 242–256, 2014.
[15] M. K. Chen and M. Sheldon, “Dynamic pricing in a labor market: Surge pricing and flexible work on the Uber platform,” in Proc. ACM Conf. Economics and Computation (EC), 2016, p. 455.
[16] I. Fette and A. Melnikov, “The WebSocket Protocol,” IETF RFC 6455, Dec. 2011.
[17] M. Jones, J. Bradley, and N. Sakimura, “JSON Web Token (JWT),” IETF RFC 7519, May 2015.
[18] S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Proc. Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 4765–4774

Laya K Shajan, Madhan Senthilkumar, Harshitha Reddy Muramreddy, Pallavi Jakkula, and Sai Inapakolla (2026). SafeGo: An Intelligent and Inclusive Safety-Centric Ride-Hailing Platform with Machine Learning-Based Risk Prediction. International Journal of Computer Science Engineering Techniques, 10(5), 213–222. ISSN: 2455-135X. DOI: https://doi.org/10.5281/zenodo.23140801