Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

US housing market forecast through ANFIS (Adaptive Neuro-Fuzzy System)

Tsouvalakis Georgios

Full record


URI: http://purl.tuc.gr/dl/dias/CF51598E-E9B2-422C-A0E9-54BC1DC7CF2B
Year 2021
Type of Item Diploma Work
License
Details
Bibliographic Citation Georgios Tsouvalakis, "US housing market forecast through ANFIS (Adaptive Neuro-Fuzzy System)", Diploma Work, School of Production Engineering and Management, Technical University of Crete, Chania, Greece, 2021 https://doi.org/10.26233/heallink.tuc.88399
Appears in Collections

Summary

Home sales in are considered to be one of the key factors influencing a country's economy. For this reason, forecasting models have been developed, where they serve us in making decisions on real estate investments and even in avoiding possible financial risks. There is a rapid increase in sales over the years, due to population growth which results in higher demand for housing. Also, the increase of productivity and the automation of many works, show a reduction of the time and the cost of construction, where it favors in the reduction of the delivery time and the immediate service of the customer. In the present project, the forecast of real estate sales is attempted, based on a neuro-fuzzy model. The model consists of an ANFIS (Adaptive Neuro-Fuzzy Inference System) controller to forecast, based on the sales data. In addition, the success rate of the model is determined by the exported MATLAB diagrams as well as the RMSE (Root Mean Square Error) error values ​​that occurred after the end of the process. In conclusion, the model reflects the dynamics of daily real estate sales that can be obtained from an ANFIS system and help predict short-term sales trends.

Available Files

Services

Statistics