Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Published Paper Details
Paper Title:
XGBoost-Based Secure Dynamic Fare Prediction for Ride-Hailing Services Using Fernet Encryption and Demand-Supply Ratio Feature Engineering with Tiered Surge Pricing
Authors Name:
S. Mushfira Mehek
, S. Mahamad Shakeer , P. Rajasekhar , K. Manoj Kumar
Dynamic pricing in ride-on-demand (RoD) services is a crucial tool for real-time optimization of supply-demand equilibrium while maximizing revenue for drivers and service providers. However, many existing approaches fail to provide proper feature engineering, transparent surge pricing mechanisms, and robust security for predictions. This paper proposes a robust and interpretable dynamic fare prediction system for RoD services using XGBoost regression combined with a demand-supply surge multiplier mechanism. The proposed sys-tem ingests multi-attribute ride request data such as number of riders and drivers, ride duration, vehicle type, booking time, loca-tion type, customer loyalty program membership, and competitor prices, while employing symmetric Fernet-based encryption to secure sensitive inputs during inference. A demand-supply ratio (DSR) feature is engineered from rider and driver counts, and a three-stage surge pricing mechanism is applied post-prediction. Experiments conducted on 1,000 samples of a ride pricing dataset
yield R2 = 0.9247, RMSE = $43.82, and MAE = $30.16.
Compared to Linear Regression, Random Forest, and Gradient Boosting baselines, XGBoost demonstrates superior accuracy and stability. Business metric estimation yields a gross margin of approximately 25%. Index Terms—Dynamic Pricing, Ride-on-Demand, XGBoost, Surge Pricing, Demand-Supply Ratio, Secure Inference, Fare Prediction, Gradient Boosting
"XGBoost-Based Secure Dynamic Fare Prediction for Ride-Hailing Services Using Fernet Encryption and Demand-Supply Ratio Feature Engineering with Tiered Surge Pricing", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2456-3315, Vol.11, Issue 4, page no.b865-b871, April-2026, Available :http://www.ijrti.org/papers/IJRTI2604255.pdf
Downloads:
000205508
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator