REALM: Automating Real Estate Appraisal with Machine Learning Models
Bibliographic record
Abstract
This paper presents REALM, an open-source tool for utilizing machine learning in real estate appraisal. The tool is built with the Django web framework, and it aims to provide researchers with a database-agnostic solution to utilize various machine-learning models in the appraisal. The platform can generate a PDF appraisal report containing the predicted price of the input property and details about the appraisal, including five comparable properties which are automatically extracted from a large database based on relevance. The tool uses the Random Forest (RF) model by default with the ability to swap models if required. Part of the research also focused on evaluating various machine learning models for price prediction using the Ames housing dataset. This involved comparing the accuracy and R2scores of Linear Regression, Neural Network, and RF models. It was found that the RF model performed price prediction with the greatest R2value, therefore it was selected as the default model for the platform. The R2scores for the price prediction model were consistently above 0.9, indicating good accuracy. Finally, methods for optimization of the model including hyperparameter tuning and the addition of bagging were tested and discussed.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.012 | 0.006 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".