Using Machine Learning to Predict Apartment Prices in Lima

Barrientos Renzo, Delgado Renzo, Escalante Laura, Febres Gonzalo, Hisbes Brizet, Chavez-Bedoya Luis (), Rosales Francisco and Vargas Willynthom
Additional contact information
Barrientos Renzo: Universidad ESAN
Delgado Renzo: Universidad ESAN
Escalante Laura: Universidad ESAN
Febres Gonzalo: Universidad ESAN
Hisbes Brizet: Universidad ESAN
Chavez-Bedoya Luis: Universidad ESAN
Rosales Francisco: Universidad ESAN
Vargas Willynthom: Universidad ESAN

A chapter in Entrepreneurship and Human-Centric Business Strategies for Social and Economic Resilience, 2026, pp 2725-2737 from Springer

Abstract: Abstract Traditional methods, such as appraisals based on comparisons or classic econo-metric models, cannot estimate apartment prices in Lima. These methods do not adequately capture the nonlinear dynamics of the market or the interaction of the various property characteristics that determine prices. This study aims to develop a prediction model for apartment prices in Lima using machine learning techniques. The following document evaluates the effectiveness of two ML models, Decision Tree and XGBoost, in predicting apartment prices in Lima. The performance of these models is compared with that of traditional hedonic regression using accuracy metrics such as mean absolute percentage error (MAPE), mean absolute error (MAE), root mean square error (RMSE), and R2. This Study sets a first guideline in the analysis of prices of apartments in Lima based on machine learning. Addressing the need for accurate real estate valuations, the study utilizes a dataset of over 40,000 records from 2014 to 2024 from the Central Reserve Bank of Peru (BCRP). Based on metrics such as MAPE, MAE, RMSE, and R2, XGBoost demonstrates superior predictive capabilities, outperforming both hedonic regression and Decision Tree models. The key price determinants identified are property size, garage availability, and location. The findings highlight machine learning’s potential to improve pricing accuracy and enable better risk assessment and investment decisions for investors, financial institutions, and regulators. The study also promotes integrating such models into credit scoring and risk management systems, which contributes to financial stability and informed policymaking in the Peruvian real estate market.

Keywords: Machine learning; XGBoost; Decision tree models; Hedonic re-gression; Risk management systems (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:prbchp:978-981-95-6415-6_168

Ordering information: This item can be ordered from
http://www.springer.com/9789819564156

DOI: 10.1007/978-981-95-6415-6_168

Access Statistics for this chapter

More chapters in Springer Proceedings in Business and Economics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().