In this study, a hybrid model based on ANFIS (Adaptive Neuro-Fuzzy Inference Systems), a predictive intelligent-based technique, and TOPSIS (Technique for Order Performance by Similarity to Ideal Solution) was implemented for sustainable supplier selection. Selection of supplier is a crucial task for companies to achieve the objectives of inbound and outbound supply chain system. This selection process may be complex due to the inclusion of diverse subjective and objective factors. There is, therefore, the need for a reliable methodology to provide higher accuracy in predictions of anticipated supplier performance, and this article makes contributions in that direction. The model was applied in the retail end of a fast-moving consumer goods (FMCG) industry to select the best possible suppliers using the sustainability criteria of the triple-bottom-line. Available data from the FMCG retail sector was fed into the TOPSIS and ANFIS model to rank the suppliers. Results indicated that the most dominant sustainability factors in the Nigerian FMCG retail sector are advanced technology, cost, reliability, on-time delivery, and environmental competencies. The finding should encourage companies in the retail sector to explore sustainability opportunities in order to improve their competitiveness for selection during bidding processes. The novelty of this study is the application of ANFIS to sustainable supplier selection problem in the context of a developing economy like Nigeria. It should also assist managers in the FMCG retail sector to highlight areas of possible sustainability improvements.

Among the modern computational techniques, Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are preferred because of their ability to deal with non-linear modelling and complex stochastic dataset. Nondeterministic models involve some computational complexities while solving real-life problems but would always produce better outcomes. For the first time, this study utilized the ANN and ANFIS models for modelling tobacco seed oil methyl ester (TSOME) production from underutilized tobacco seeds in the tropics. The dataset for the models was obtained from an earlier study which focused on design of the experiment on TSOME production. This study is an an exposition of the influence of transesterification parameters such as reaction duration (T), methanol/oil molar ratio (M:O), and catalyst dosage on the TSOME/biodiesel yield. A multi-layer ANN model with ten hidden layers was trained to simulate the methanolysis process. The ANFIS approach was further implemented to model TSOME production. A comparison of the formulated models was completed by statistical criteria such as coefficient of determination (R²), mean average error (MAE), and average absolute deviation (AAD). The R² of 0.8979, MAE of 4.34468, and AAD of 6.0529 for the ANN model compared to those of the R² of 0.9786, MAE of 1.5311, and AAD of 1.9124 for the ANFIS model. The ANFIS model appears to be more reliable than the ANN model in predicting TSOME production in the tropics.