Monitoring and intervening in water quality at wastewater treatment plants play a crucial role in their management. When designing and operating wastewater treatment plants, the biological oxygen demand (BOD) values are essential. However, measuring this parameter takes longer compared to other parameters, and conducting experiments for BOD measurement can be both laborious and costly. In this study, the aim was to predict the biological oxygen demand value using artificial neural networks and multiple regression analysis techniques through easily measurable parameters in wastewater treatment plants. The measurement data used in the study covered the years 2021-2022 and was obtained from a wastewater treatment plant in Van province, Turkey. The selected input parameters for prediction were pH, electrical conductivity, temperature, dissolved oxygen, chemical oxygen demand, suspended solids, total nitrogen, and total phosphorus, while the biological oxygen demand value was chosen as the dependent variable. The results of the predictions using artificial neural network model were as follows: Mean Absolute Percentage Error (MAPE) was 0.12%, Mean Absolute Deviation (MAD) was 0.04, the coefficient of determination (R) was 99.83%, and R-squared (R2) was 99.68%. Likewise, using multiple regression analysis, the prediction model for BOD yielded a MAPE of 0.68%, MAD of 0.06, R of 96.40%, and R2 of 92.92%. The findings obtained in the study, it is possible to predict the biological oxygen demand value using feedforward artificial neural networks and linear multiple regression analysis techniques with the help of easily measurable parameters. When comparing both models, it was determined that the model developed using artificial neural networks performed better than the one developed using multiple regression analysis..