A major task that the NLP (Natural Language Processing) has to follow is Sentiments analysis (SA) or opinions mining (OM). For finding whether the user's attitude is positive, neutral or negative, it captures each user's opinion, belief, and feelings about the corresponding product. Through this, needed changes can well be done on the product for better customer contentment by the companies. Most of the existing techniques on SA for these online products encompass very low accuracy and also consumed more time during training. By utilizing a Deep learning modified neural network (DLMNN), a method is proposed for SA of online product review and by means of Improved Adaptive Neuro-Fuzzy Inference System (IANFIS), a method is proposed for future prediction of online products to trounce the above-stated issues. Initially, the data values are partitioned into Grade-based (GB), Content-based (CB), and Collaboration based (CLB) scenarios from the dataset. After that, each scenario goes through review analysis (RA) by utilizing DLMNN, which brings about the results as positive, negative, as well as neutral reviews. IANFIS performs a weighting factor and classification on the product for future prediction. In the experimental evaluation, the proposed system gave a better performance compared to the existing methods.