A Hybrid Spatio-Temporal Decision Tree Architecture for Micro-Localized Land Valuation: A Case Study in Eastern Side of Godhra Town

Author(s)	Mr. Ansh D. Shah, Ms. Krishna D. Sheth, Mr. Harishkumar S. Sheth, Prof. Amit K. Yadav, Prof. Dr. Sanskriti S. Mujumdar
Country	India
Abstract	Conventional global regression models frequently do not adequately represent the discrete, non-linear spatial boundaries intrinsic to real estate valuation. This paper introduces an innovative hybrid machine learning architecture aimed at forecasting localized land rates in Eastern Side of Godhra Town, Gujarat. The proposed model removes Runge's oscillation by replacing continuous global polynomial regressions with localized Spatial Indicator Functions (Decision Trees) and Core Algorithmic Approaches (Engines) and Functional Synonyms (Process-Oriented). It also captures exact micro-neighborhood pricing behaviors. The architecture that came out of this had a continuous-time R2 of 0.995. Also, to make sure that the model could be used in legacy computing environments without relying on Python, its mathematical graph was successfully turned into a native, macro-free spreadsheet logic architecture.
Keywords	Real Estate Valuation, Land Rate Prediction, Spatial Modeling, Non-Linear Regression, Machine Learning in Real Estate, Property Price Estimation, Hybrid Machine Learning Architecture, Spatial Heterogeneity, etc.
Field	Engineering
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-03-20

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research