Copyright © 2026 Authors retain the copyright of this article. This article 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.

@article{186374,
        author = {Prajwal Halmare and Prof. Rashmi Janbandhu and Riteshkumar Gaure and Rajat Ranka},
        title = {Player’s Performance Prediction Model for Cricket},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {6},
        pages = {1009-1016},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186374},
        abstract = {Abstract— In sports analytics, typical predictive models are often based solely on historical statistics, therefore there is no consideration of a player's current range of biomechanics and technique. This basic problem leads to underdeveloped and inaccurate performance predictions. This study presents a new solution to overcome this issue: a totally new Dual-Perspective Analytics Platform designed for the specific purpose of providing a more complete, whole-data approach to assessing performance, which uses a mixture of longitudinal performance data and technical assessment in real-time.
The Statistical Forecasting Module uses a Linear Regression model, meticulously trained on all historical data from 2008 to 2024 from IPL and International, to accurately quantify expected long-term performance. This module provides two analytical outputs: a numerical forecasting estimation of future run-scoring ability (validated 80% to 85% accuracy) and a detailed examination of player output, by team membership, in each of the respective seasons. These two components benefit analysts, providing a specific snapshot of anticipated player performance and how performance variability changes under differing team conditions.
Along with the statistical estimates, the Biomechanical Analysis Module utilizes MediaPipe Pose and computer vision approaches to provide an objective evaluation of current player technique from video content. This assessment measures specific kinematic metrics—Backlift Quality, Head Stability, and Footwork Quality—so that they can be summarized as individual metrics and compared in total as a Technical Score. The combination of long-term statistical prediction with real- time technical assessment leads to a Selection Recommendation that can be scaled against a professional normative standard, defined as 15.00. This platform converts the inherently subjective observations of coaching into systematized, objective variables for planning purposes.},
        keywords = {Index Terms— Cricket Analytics, Performance Prediction, Machine Learning in Cricket, Computer Vision, Pose Estimation},
        month = {March},
        }