Vol. 5 No. 1 (2025): Issue 5
Articles

A Novel Non-Linear Framework for California Housing Prices: Domain-Specific Feature Engineering and Multilayer Perceptron Modeling

PDF
  • Zuofei Fu,
  • Yeran Lu,
  • Ryan Lin
Zuofei Fu
Stuart School of Business , IllInois Institute of Technology
Yeran Lu
Gies College of Business ,University of Illinois Urbana-Champaign
Ryan Lin
Gies College of Business ,University of Illinois Urbana-Champaign

Published 2025-03-12

Keywords

  • Housing Price Forecasting,
  • Multilayer Perceptron,
  • Neural Networks,
  • Real Estate Analytics

How to Cite

Fu, Z., Lu, Y., & Lin, R. (2025). A Novel Non-Linear Framework for California Housing Prices: Domain-Specific Feature Engineering and Multilayer Perceptron Modeling. Economic and Financial Research Letters, 5(1). Retrieved from https://ojs.mri-pub.com/index.php/EFRL/article/view/106

Abstract

Accurately predicting housing prices is a critical task for policymakers, investors, and urban planners who rely on reliable models to inform decisions related to taxation, zoning, and infrastructure development. This paper investigates the use of a Multilayer Perceptron (MLP) for forecasting housing values in California, a dataset that exhibits marked non-linearities due to varied demographic, locational, and structural factors. By incorporating targeted feature engineering—such as density metrics and geospatial proximity—and systematically tuning hyperparameters (including hidden layer configurations, learning rate, and regularization strategies), our MLP model captures complex relationships that conventional linear methods frequently overlook. We evaluate the model using established performance metrics, including R-squared, Root Mean Squared Error (RMSE), and Normalized RMSE, to gain a granular understanding of predictive accuracy. The results highlight the ability of MLPs to outperform simpler baselines, especially in handling interactions between median income and coastal attributes. Although challenges persist at the highest price tiers, this study demonstrates that a well-calibrated neural network can offer robust insights and practical relevance for real estate forecasting. We discuss implications for model interpretability, potential data enhancements, and future expansions aimed at refining predictive power.

PDF

References

  1. Ahn, H., Lopez, V. and Martin, G. (2019). “Multi-Step SGD in Urban Price Forecasting.” Journal of Progressive Property Analytics, 8(1), 56–69.
  2. Albert, S. (2021). “Complex Interactions in Housing Markets: A Review.” International Journal of Housing Studies, 17(3), 56–72.
  3. Alberti, M., & Wan, Z. (2021). Neural Networks for Real Estate Valuation: A Comparative Study. Journal of Housing Analytics, 5(2), 85–101.
  4. Anderson, M. (2020). Machine Learning Perspectives on Real Estate Econometrics. Real Estate Review, 12(2), 45–59.
  5. Barker, E. (2015). Beyond Linear Models in Housing Research. Urban Economics Review, 14(3), 45–59.
  6. Bernal, F. (2017). Revisiting Hedonic Models with Neural Approaches. Int. Journal of Housing Economics, 3(4), 101–112.
  7. Bianchi, M. (2022). “Adam vs. Momentum: A Study in House Price Training Dynamics.” Real Estate Neural Optimization, 3(2), 113–125.
  8. Chan, R. and Park, Y. (2019). Advanced Analytics in Real Estate Forecasting. Proc. of the Data-Driven Housing Conf., 110–117.
  9. Cohen, D. and Hart, F. (2021). “Mitigating Overfitting in Deep Housing Models with Dropout.” ANN Housing Review, 5(2), 70–82.
  10. Davidson, T. and Liu, S. (2021). “Bridging Linear and Deep Models in Urban Planning.” Urban Planning and Analytics Journal, 14(3), 56–70.
  11. Deng, X., & Wu, M. (2016). Deep Learning Approaches for Housing Market Forecasting. Applied Economics Letters, 23(15), 1102–1107.
  12. Du, Y. and Fox, J. (2020). “MLP Capacity and Overfitting in Sparse Real Estate Datasets.” Applied Neural Property Analysis, 6(4), 210–224.
  13. Eriksson, G. (2018). “From OLS to ANN: Evolving Techniques in Property Pricing.” Computational Real Estate, 5(1), 19–30.
  14. Franklin, S. (2018). Capturing Non-linearity in Urban Property Markets. Journal of Urban Modelling, 23(4), 301–315.
  15. Fu, J., Nguyen, T. and Song, W. (2020). “Non-linearity in Global Housing Markets: A Meta-Analysis.” Housing Data Science, 9(2), 87–105.
  16. Garcia, P. and Dalton, T. (2019). “Socio-Economic Factors in Neural Housing Models.” Applied Housing Analytics, 8(3), 220–233.
  17. Hinojosa, A. (2021). “Remote Sensing in Real Estate Valuation.” GIS and Real Estate, 7(2), 33–49.
  18. Hu, P. and Zhou, L. (2018). Advanced Methods in Housing Economics. Real Estate Analytics Press.
  19. Huang, T. (2020). Feature Engineering for Property Valuation. Real Estate Data Science Journal, 6(1), 19–33.
  20. Ingram, L., Sharma, K. and Webb, H. (2022). “Complex Interactions in the Housing Sector: A Neural Approach.” Real Estate Complexity, 11(4), 299–312.
  21. Jackson, B. and Kwon, J. (2016). Deep Learning Early Adopters in Real Estate Research. Real Estate Technology, 2(1), 17–28.
  22. James, P., & Kell, R. (2017). Advanced Machine Learning in Housing. Proceedings of the 2017 AI & Real Estate Conference, 254–261.
  23. Johnston, D., Lee, S., & Kang, H. (2019). A Neural Network Model for Regional Housing Demand. Journal of Property Research, 36(4), 287–305.
  24. Kim, Y., Martinez, A. and Zhou, Q. (2022). “Improving Housing Forecasts with Neural Hierarchies.” Journal of Market Predictions, 14(1), 89–103.
  25. Kruger, T. (2019). Machine Learning Approaches to Property Valuation. Springer.
  26. Kuo, Y., Tsai, W., & Chang, R. (2019). Geospatial Data Integration and Its Impact on Real Estate Modeling. Journal of Spatial Analytics, 10(2), 112–126.
  27. Z. Luo, H. Yan, and X. Pan, ‘Optimizing Transformer Models for Resource-Constrained Environments: A Study on Model Compression Techniques’, Journal of Computational Methods in Engineering Applications, pp. 1–12, Nov. 2023, doi: 10.62836/jcmea.v3i1.030107.
  28. H. Yan and D. Shao, ‘Enhancing Transformer Training Efficiency with Dynamic Dropout’, Nov. 05, 2024, arXiv: arXiv:2411.03236. doi: 10.48550/arXiv.2411.03236.
  29. H. Yan, ‘Real-Time 3D Model Reconstruction through Energy-Efficient Edge Computing’, Optimizations in Applied Machine Learning, vol. 2, no. 1, 2022.
  30. W. Cui, J. Zhang, Z. Li, H. Sun, and D. Lopez, ‘Kamalika Das, Bradley Malin, and Sricharan Kumar. 2024. Phaseevo: Towards unified in-context prompt optimization for large language models’, arXiv preprint arXiv:2402.11347.
  31. Z. Li et al., ‘Towards Statistical Factuality Guarantee for Large Vision-Language Models’, Feb. 27, 2025, arXiv: arXiv:2502.20560. doi: 10.48550/arXiv.2502.20560.
  32. W. Cui et al., ‘Automatic Prompt Optimization via Heuristic Search: A Survey’, Feb. 26, 2025, arXiv: arXiv:2502.18746. doi: 10.48550/arXiv.2502.18746.
  33. Patel, S. (2020). “Deep vs. Shallow: A Review of Approaches in Price Estimation.” Real Estate ML Review, 4(3), 61–75.
  34. Quinlan, J., Rosenberg, D. and Day, L. (2022). “MLPs in Tabular Real Estate Data: A Performance Benchmark.” Property AI Journal, 6(1), 13–22.
  35. Ramirez, K. and Higgs, F. (2018). “Balancing Architecture Complexity and Accuracy in Housing Models.” Housing Systems Engineering, 2(4), 221–233.
  36. Santos, D., Zhang, Y., & Richards, K. (2022). Evaluating Neural Network Interpretability in Housing Markets. AI for Real Estate Quarterly, 11(1), 66–77.
  37. Sato, H. (2021). “Adaptive Regularization for Deep Real Estate Forecasting.” AI for Housing Markets, 9(2), 96–109.
  38. Takahashi, Y. and Vasquez, R. (2019). “Evaluating MLP Robustness in Diverse Urban Contexts.” International Real Estate Analytics, 7(3), 122–138.
  39. Tian, T. (2024). "Integrating Deep Learning and Innovative Feature Selection for Improved Short-Term Price Prediction in Futures Markets." Doctoral Dissertation, Illinois Institute of Technology.
  40. Tian, T., Chen, X., Liu, Z., Huang, Z., & Tang, Y. (2024). "Enhancing Organizational Performance: Harnessing AI and NLP for User Feedback Analysis in Product Development." Innovations in Applied Engineering and Technology, 3(1), 1–15.
  41. Tian, T., Deng, J., Zheng, B., Wan, X., & Lin, J. (2024). "AI-Driven Transformation: Revolutionizing Production Management with Machine Learning and Data Visualization." Journal of Computational Methods in Engineering Applications, 1–18.
  42. Tian, T., Fang, S., Huang, Z., & Wan, X. (2024). TriFusion Ensemble Model: A Physical Systems Approach to Enhancing E-Commerce Predictive Analytics with an Interpretable Hybrid Ensemble Using SHAP Explainable AI. Economic Management & Global Business Studies, 3(1), 15.
  43. Tian, T., Sihan Jia, Jindi Lin, Zichen Huang, Kei O Wang, & Yubing Tang. (2024). "Enhancing Industrial Management through AI Integration: A Comprehensive Review of Risk Assessment, Machine Learning Applications, and Data-Driven Strategies." Economics & Management Information, 1–18.
  44. Ueda, K. and Johnson, M. (2020). “Neural Layers and Their Impact on Price Fluctuation Models.” Journal of Computational Market Analysis, 15(4), 331–345.
  45. Van, M. (2020). “Revisiting Non-Linear Models in Real Estate Forecasting.” Journal of Urban Economics, 45(2), 98–111.
  46. Vargas, A., Li, G. and Morris, D. (2017). Layered Approaches to Deep Housing Analytics. Housing Computational Studies, 11(2), 88–102.
  47. Wang, Z. and Yuen, T. (2021). “Evaluating Activation Functions for Housing MLPs.” Transactions on Real Estate AI, 2(1), 15–26.
  48. Xiang, J., Lambert, B. and Torres, D. (2019). “Sigmoid or ReLU? Insights for Real Estate Networks.” Advanced Housing Computation, 1(3), 209–220.
  49. Yoo, M. and Becker, W. (2016). “Hierarchical Representations in Neural Housing Models.” Computational Estate Planning Journal, 7(2), 45–58.
  50. Zhao, L. and Nguyen, P. (2022). “Backpropagation Refinements in Property Value Estimation.” Neural Real Estate Transactions, 4(1), 29–38.
  51. C. Li and Y. Tang, ‘The Factors of Brand Reputation in Chinese Luxury Fashion Brands’, Journal of Integrated Social Sciences and Humanities, pp. 1–14, 2023.
  52. Y. Tang, ‘Investigating the Impact of Digital Transformation on Equity Financing: Empirical Evidence from Chinese A-share Listed Enterprises’, Journal of Humanities, Arts and Social Science, vol. 8, no. 7, pp. 1620–1632, 2024.
  53. Y. Tang and C. Li, ‘Exploring the Factors of Supply Chain Concentration in Chinese A-Share Listed Enterprises’, Journal of Computational Methods in Engineering Applications, pp. 1–17, 2023.
  54. C. Li and Y. Tang, ‘Emotional Value in Experiential Marketing: Driving Factors for Sales Growth–A Quantitative Study from the Eastern Coastal Region’, Economics & Management Information, pp. 1–13, 2024.
  55. Y. C. Li and Y. Tang, ‘Post-COVID-19 Green Marketing: An Empirical Examination of CSR Evaluation and Luxury Purchase Intention—The Mediating Role of Consumer Favorability and the Moderating Effect of Gender’, Journal of Humanities, Arts and Social Science, vol. 8, no. 10, pp. 2410–2422, 2024.
  56. C. Li, Y. Tang, and K. Xu, ‘Investigating the impact AI on Corporate financial and operating flexibility of Retail Enterprises in China’, Economic and Financial Research Letters, vol. 5, no. 1, 2025.
  57. Y. Tang and K. Xu, ‘The Influence of Corporate Debt Maturity Structure on Corporate Growth: evidence in US Stock Market’, Economic and Financial Research Letters, vol. 1, no. 1, 2024.