Nutritionally enriched pineapple rasgulla can be produced through different methods and visual appearance being the most vital concern for the consumer acceptance. Therefore, total colour difference of the processed products should be optimized for better marketability. The central composite design (CCD) was adopted to design the experimental runs, response surface methodology was implemented to study the predictive models for hot air dried (HA), microwave dried (MW), microwave convective dried (MWC) and freeze dried (FD) pineapple fortified rasgulla along with fresh pineapple pulp (PR) fortified rasgulla. Artificial neural network (ANN) model was developed for all of the above mentioned rasgulla samples and optimization was attained by coupling the ANN model with particle swarm optimization (PSO) methodology. The non-linear rasgulla processing was modeled by using the input parameters like oven temperature (for HA), microwave power level (for MW), drying temperature (for MWC), pineapple percentage, cooking time (for HA, MW, MWC, FD and PR) and output as total colour difference. The optimum results obtained at oven temperature of 58.51 ​°C, 30.27% of pineapple and cooking time of 14.32 ​min (HA); microwave power level of 100 ​W, 35% of pineapple and cooking time of 13.51 ​min (MW); drying temperature of 100 ​°C, 35% of pineapple and cooking time of 15 ​min (MWC); 35% of pineapple for both FD and PR, while the cooking time of 12.57 and 15 ​min for FD and PR respectively.