Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Predicting Rental Price of Lane Houses in Shanghai with Machine Learning Methods and Large Language Models

Tingting Chen, Shijing Si

TL;DR

This paper addresses predicting Shanghai lane-house rental prices by benchmarking traditional machine learning methods against a ChatGPT-based LLM approach. It uses a Kaggle dataset of about $2{,}609$ 2021 lane-house rentals and evaluates models with $MSE$, $MAE$, and $R^2$ to assess predictive accuracy. Random Forest among traditional models shows strong performance while ChatGPT in 10-shot prompting achieves the highest $R^2$, suggesting LLMs can surpass traditional models with sufficient contextual data. The work demonstrates the potential of integrating LLMs into real estate pricing workflows, enabling flexible handling of unstructured information and context-rich predictions.

Abstract

Housing has emerged as a crucial concern among young individuals residing in major cities, including Shanghai. Given the unprecedented surge in property prices in this metropolis, young people have increasingly resorted to the rental market to address their housing needs. This study utilizes five traditional machine learning methods: multiple linear regression (MLR), ridge regression (RR), lasso regression (LR), decision tree (DT), and random forest (RF), along with a Large Language Model (LLM) approach using ChatGPT, for predicting the rental prices of lane houses in Shanghai. It applies these methods to examine a public data sample of about 2,609 lane house rental transactions in 2021 in Shanghai, and then compares the results of these methods. In terms of predictive power, RF has achieved the best performance among the traditional methods. However, the LLM approach, particularly in the 10-shot scenario, shows promising results that surpass traditional methods in terms of R-Squared value. The three performance metrics: mean squared error (MSE), mean absolute error (MAE), and R-Squared, are used to evaluate the models. Our conclusion is that while traditional machine learning models offer robust techniques for rental price prediction, the integration of LLM such as ChatGPT holds significant potential for enhancing predictive accuracy.

Predicting Rental Price of Lane Houses in Shanghai with Machine Learning Methods and Large Language Models

TL;DR

This paper addresses predicting Shanghai lane-house rental prices by benchmarking traditional machine learning methods against a ChatGPT-based LLM approach. It uses a Kaggle dataset of about 2021 lane-house rentals and evaluates models with , , and to assess predictive accuracy. Random Forest among traditional models shows strong performance while ChatGPT in 10-shot prompting achieves the highest , suggesting LLMs can surpass traditional models with sufficient contextual data. The work demonstrates the potential of integrating LLMs into real estate pricing workflows, enabling flexible handling of unstructured information and context-rich predictions.

Abstract

Housing has emerged as a crucial concern among young individuals residing in major cities, including Shanghai. Given the unprecedented surge in property prices in this metropolis, young people have increasingly resorted to the rental market to address their housing needs. This study utilizes five traditional machine learning methods: multiple linear regression (MLR), ridge regression (RR), lasso regression (LR), decision tree (DT), and random forest (RF), along with a Large Language Model (LLM) approach using ChatGPT, for predicting the rental prices of lane houses in Shanghai. It applies these methods to examine a public data sample of about 2,609 lane house rental transactions in 2021 in Shanghai, and then compares the results of these methods. In terms of predictive power, RF has achieved the best performance among the traditional methods. However, the LLM approach, particularly in the 10-shot scenario, shows promising results that surpass traditional methods in terms of R-Squared value. The three performance metrics: mean squared error (MSE), mean absolute error (MAE), and R-Squared, are used to evaluate the models. Our conclusion is that while traditional machine learning models offer robust techniques for rental price prediction, the integration of LLM such as ChatGPT holds significant potential for enhancing predictive accuracy.
Paper Structure (29 sections, 10 equations, 6 figures, 4 tables)

This paper contains 29 sections, 10 equations, 6 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Current Research Status on Rental Houses
  4. Machine Learning Methods
  5. Large Language Models in Predictive Tasks
  6. DATA PREPROCESSING
  7. Quantization of ordinal variables
  8. Quantification of dummy variables
  9. Data Analysis
  10. MACHINE LEARNING MODEL SELECTION
  11. Multiple Liner Regression
  12. Ridge Regression
  13. Lasso Regression
  14. Decision Tree
  15. Random Forest
  16. ...and 14 more sections

Figures (6)

  • Figure 1: Distribution of rental properties in different regions.
  • Figure 2: distribution of rental prices in different regions.
  • Figure 3: Distribution of property sizes in different regions.
  • Figure 4: distribution of total soft furnishing facilities.
  • Figure 5: Comparison of different methods.
  • ...and 1 more figures