Enhancing Real Estate Recommendation through Deeplearning

Abstract

There has been a rise in the total amount of knowledge that is being disseminated across various internet platforms. There is a reasonable decline in the implement behavior of the necessary information for a user when there is a better level of precision when there is a bigger amount of information. This is because the amount of information is increasing. The implication of this is that, as a result of the ever-increasing growth of network systems, users may find it difficult to acquire the relevant data they require through utilizing the online method in the context of a large and perplexing ecosystem. Consumers can find what they are looking for with the assistance of the recommendation engine, which provides them with potential goods that may be of interest to them. It typically takes use of preexisting relationships amongst users and/or objects in order to predict people's interest for things, and it does this by analyzing the connections between customers and products. The scientific research group as well as those working in social design engineering are now showing a substantial amount of curiosity in the recommender system. Consequently, the purpose of this study piece was to propose an efficient approach for the purpose of generating real estate recommendations by using K-nearest Neighbor Segmentation in conjunction with Artificial Neural Networks as well as Decision Making. The experimental assessment has been carried out, which has shown that the approach that was originally offered is preferable