Model Hybrid for Sales Forecast for the Housing Market of São Paulo

Abstract

This research proposes a combined model of time series for forecasting housing sales in the city of São Paulo. We used data referring to the time series of sales of residential units provided by SECOVI-SP. The Exponential Softening, Box-Jenkins and Artificial Neural Networks models are individually modelled, later these are combined through five forecast combination techniques.The techniques used are Arithmetic Mean, Geometric Mean, Harmonic Mean, Linear Regression and Principal Component Analysis. The measures of accuracy to measure the results obtained and to select the best model are the RMSE, MAPE and UTheil of forecast. The results showed that Linear Regression with an independent variable, being a combination of the SARIMA model (2,0,0)(2,0,0)12 and MLP/RNA (12,10,1), provided a satisfactory performance, with an RMSE of 368.74, MAPE of 19.2% and UTheil of 0.315.The combination of time series models allowed a significant increase in forecast performance. Finally, the model was validated, using it to predict housing sales. The results show that the model has a good fit, thus demonstrating that using a housing sales forecasting model helps industry professionals minimize error and make sales and launch decisions.

Property Management Enabled by Artificial Intelligence Post Covid-19: An Exploratory Review and Future Propositions

“…A broader approach was taken by Moro et al (2020), who combined five forecast combination techniques and proposed a combined model to forecast property sales using time series data and by modelling using the Box-Jenkins, exponential softening, and ANN techniques. Zlateva et al (2011) assessed the investment risks in real estate for sustainable regional development and proposed a fuzzy logic model as a hierarchical system with various variables.…”

Applied aspects of time series models for predicting residential property prices in Bulgaria

“…According to Miller et al (2011), housing prices play an important role in GDP growth. Furthermore, civil construction is one of the leading sectors of the economy (Moro et al, 2020), and real estate is a medium and long-term investment industry, which has a long return period (Huang et al, 2011). Last but not least, the real estate market is mainly determined by the financial market (Anghel & Hristea, 2015).…”

The Prediction of Douyin Live Sales based on Neural Network Algorithms

“…Through experiments, they found that the addition of Google Trends data could reduce the mean absolute percentage error (MAPE) by 2.2% to 7.7%. To predict housing sales in São Paulo, Moro et al [6] modeled the index softening, Box-Jenkins, and artificial neural network models and compared their effects using different combinations. Ma et al [7] applied the genetic algorithm-back-propagation neural network (GA-BPNN) algorithm to the sales forecast of electric vehicles.…”