DOI: 10.7763/IJCTE.2026.V18.1388
Harnessing Explainable AI and Machine Learning for Dual Predictive Modeling of Car Goodwill and Crop MSP in Price and Policy Forecasting
2. Department of Electronics and Communication Engineering, Amal Jyothi College of Engineering (Autonomous), Kanjirappally, Kerala, India
Email: meghnachaudhary828@gmail.com (M.C.); aalam@jamiahamdard.ac.in (M.A.A.); sherin.zafar@jamiahamdard.ac.in (S.Z.); kmabubeker82@gmail.com (K.M. A.)
*Corresponding author
Manuscript received February 12, 2025; revised April 15, 2025; accepted November 25, 2025; published March 17, 2026
Abstract—Accurate yet interpretable forecasting remains a major challenge in data-driven price and policy decision-making, as many machine learning models prioritize predictive performance while offering limited transparency. To address this gap, this study proposes an integrated Explainable Artificial Intelligence (XAI)—enabled machine learning framework for dual predictive modelling across two economically significant domains: automotive valuation and agricultural price policy. The framework simultaneously predicts car goodwill values and crop Minimum Support Prices (MSP), enabling cross-domain analysis while maintaining model interpretability. Comparative experiments are conducted using multiple machine learning techniques, including linear and ensemble-based models, applied to automotive and agricultural datasets. Ensemble methods demonstrate superior predictive capability in both domains. To enhance transparency and stakeholder trust, XAI techniques are incorporated to explain model behaviour and identify key influencing factors. The analysis shows that depreciation and brand-related attributes play a dominant role in car goodwill valuation, whereas climatic and cost-related factors significantly influence MSP predictions. The results confirm that integrating XAI with machine learning improves both predictive reliability and interpretability, transforming black-box models into actionable decision-support systems. The proposed dual predictive framework offers a scalable and transparent approach for market optimization and policy evaluation, highlighting the practical value of explainable AI in strategic economic planning and data-driven governance.
Keywords—Explainable Artificial Intelligence (XAI), goodwill car values, crop Minimum Support Price (MSP), linear regression, random forest, decision tree, gradient boosting, XGBoost and Marketing Mix Modelling (MMM)
Cite: Meghna Chaudhary, Mohammad Afshar Alam, Sherin Zafar, and Kiliyanal Muhammedkunju Abubeker, "Harnessing Explainable AI and Machine Learning for Dual Predictive Modeling of Car Goodwill and Crop MSP in Price and Policy Forecasting," International Journal of Computer Theory and Engineering, vol. 18, no. 1, pp. 48-67, 2026.
Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).