BACKGROUND: Integrated pest management (IPM) in European glasshouses has substantially advanced in automated insect pest detection systems lately. However, transforming such an enormous data influx into optimal biological control strategies remains challenging. In addition, most biological control forecast studies relied on the single-best model approach, which is susceptible to overconfidence, and they lack validation over sufficient sampling repetitions where robustness remains questionable. Here we propose employing an unweighted ensemble model, by combining multiple forecasting models ranging from simple models (linear regressions and Lotka-Volterra model) to machine learning models (Gaussian process, Random Forest, XGBoost, Multi-Layer Perceptron), to predict 1-week-ahead population of western flower thrips (Frankliniella occidentalis), a notorious pest in glasshouses, under the influence of its biological control agent Macrolophus pygmaeus in pepper-growing glasshouses. RESULTS: Models were trained with only 1 year of data, validated over 3 years of monitoring of multiple compartments to evaluate their robustness. The full ensemble model outperformed the Naïve Forecast in 10 out of 14 compartments for validation, with around 0.451 and 26.6% increase in coefficient of determination (R CONCLUSION: Our results demonstrated the benefits of the ensemble model over the traditional 'single-best model' approach, avoiding model structural biases and minimizing the risk of overconfidence. This showcased how an ensemble model with minimal training data can assist growers in fully utilizing the pest monitoring data and support their decision-making on IPM. © 2025 Society of Chemical Industry.