Yellow Stem Borer (YSB) (Scirpophaga incertulas) is one of the most destructive pests affecting rice production in India, causing significant yield losses across different agro-climatic regions. Accurate forecasting of YSB populations is crucial for timely pest management and minimizing crop damage. This study evaluates the performance of statistical and machine learning models for predicting YSB populations using weekly pest incidence data collected from five research stations in Andhra Pradesh (Nellore, Maruteru, Bapatla, Ragolu, and Nandyal) over multiple years. The study employs Integer-Valued Generalized Autoregressive Conditional Heteroskedastic (INGARCH) models along with Artificial Neural Networks (ANN), Support Vector Regression (SVR), Extreme Learning Machines (ELM), and their hybrid counterparts (INGARCH-ANN, INGARCH-SVR, and INGARCH-ELM) to improve forecasting accuracy. Results indicate that hybrid models, particularly NBINGARCH-ELM, consistently outperformed standalone models in terms of Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) across different locations and seasons. The findings reveal that YSB populations are significantly influenced by climatic factors such as temperature, relative humidity, and rainfall, with distinct seasonal patterns. The Box-Pierce test confirmed minimal autocorrelation in residuals for most models, validating their reliability. These results highlight the potential of hybrid statistical machine learning models for pest forecasting, providing valuable insights for integrated pest management (IPM) strategies. Future research can further enhance these models by incorporating additional environmental and agronomic variables for improved precision in pest outbreak predictions.