11th International Conference on ICTIS

Authors - Hiren Darji, Devarsh Chandiwade, Tushar Panchal, Meenakshi Chandra, Swapnil Gharat
Abstract - Strategic decision making in time dependent systems often involves complex trade-offs between short-term performance gains and long-term degradation effects. Designing effective strategies in such environments requires accurate modelling of performance evolution and careful evaluation of discrete intervention decisions. This paper presents an intelligent strategy simulation framework that integrates data-driven modelling and predictive analytics to evaluate decision strategies under progressive performance degradation. Using high-frequency Formula 1 telemetry data as a representative case study, the proposed framework models lap-time evolution as a function of degradation age and operational context. Both regression-based models and neural network predictors are employed to estimate performance trends, enabling comparison between linear baselines and nonlinear learning approaches. A simulation engine is then used to evaluate multiple strategic scenarios by incorporating degradation dynamics and discrete intervention penalties, allowing quantitative assessment of alternative decision policies. The framework enables direct comparison of strategy outcomes through cumulative performance metrics and visual race progress analysis, providing interpretable decision support. Experimental results demonstrate that both degradation rate and decision timing have a signi􀏐icant impact on overall system performance. Furthermore, neural network models consistently outperform linear regression in capturing non-linear degradation behaviour, particularly during extended operational phases. Although demonstrated using motorsport telemetry data, the proposed approach is generalizable to a wide range of real world optimization and decision-support problems involving degradation, uncertainty, and staged decision points.