A Data Driven Risk Assessment in Fractional investment in Commercial Real Estate using Deep Learning Model and Fog Computing Infrastructure.

Abstract

Fractional investments in commercial real estate are becoming increasingly popular, there is an ever-increasing demand for efficient risk assessment methodologies. The deep learning proved their high accuracy for data driven models. In this paper, a deep learning In order to analyze and forecast the risk that is associated with fractional investments, we offer a deep learning system that makes use of a dataset that contains a variety of property qualities, financial indicators, market situations, and investor characteristics. Our algorithm is able to discover intricate patterns and correlations within the data by utilizing CLSTM, which enables it to accurately anticipate risk. Through the use of experiments with our datasets, we are able to show the effectiveness of our methodology, producing encouraging results in detecting and quantifying risk variables. As a result of this research, risk management methods in fractional commercial real estate investments are being advanced, and investors and stakeholders are receiving useful information that may help them make more educated decisions.

Keywords: