Scribd
Upload
16 views12 pages

Aiml Exp9-10

Uploaded by

Aakash Mokani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
16 views12 pages

Aiml Exp9-10

Uploaded by

Aakash Mokani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 12

Exp 9 & 10: Mini Project

2022300053: Shardul Mahindrakar


2022300057: Piyush Mehta
2022300061: Aayush Mohite

Study from research papers:

1. "House Price Prediction Using Machine Learning Algorithms: A Case


Study of Bangalore"

● Summary: This paper explores various machine learning algorithms for predicting house prices
in Bangalore, including Linear Regression, Decision Trees, and Random Forest. It emphasizes the
impact of location, area, and amenities on price and compares algorithm performance based on
RMSE and R² scores.
● Key Takeaway: Random Forest performed the best in terms of accuracy, highlighting the
importance of non-linear models for capturing complex relationships in the data.

2. "A Comparative Study of Machine Learning Models for Predicting


Housing Prices"

● Summary: The authors evaluate multiple algorithms like XGBoost, k-Nearest Neighbors (k-
NN), and Support Vector Machines (SVM) on a housing dataset. They focus on preprocessing
techniques like feature scaling and log transformation for skewed data and analyze feature
importance.
● Key Takeaway: XGBoost outperformed other models, especially after feature scalingand log
transformations were applied, demonstrating that advanced ensemble models and proper
preprocessing are crucial for accurate predictions.

3. "Real Estate Price Prediction Using Ensemble Learning Models"

● Summary: This study applies ensemble methods such as Gradient Boosting Machines (GBM)
and stacking models (a combination of multiple algorithms). The dataset includes location-
specific features, and the authors experiment with feature engineering techniques like clustering
to capture neighborhood patterns.
● Key Takeaway: Stacking models combining Random Forest, XGBoost, and Linear Regression
achieved the highest accuracy, suggesting that blending multiple models can provide better
generalization in house price prediction.

4. "Predicting Real Estate Prices Using Artificial Neural Networks and


Machine Learning Models"
● Summary: This paper compares traditional machine learning models with Artificial Neural
Networks (ANN) for real estate price prediction. It explores hyperparameter tuning and
discusses the challenges of neural network training with limited datasets.
● Key Takeaway: Although ANN was computationally more intensive, it achieved
competitive results when enough data was available, indicating its potential when
combined with robust data sources and feature engineering.

5. "Analyzing Housing Market Dynamics with Spatio-Temporal Modeling


and Machine Learning"

● Summary: This paper integrates time-series data with housing market data to capture trends
over time using LSTM and Random Forest. It includes variables like monthly interest rates,
economic indicators, and property features, providing a dynamic model of price trends.
● Key Takeaway: LSTM performed well in capturing temporal dependencies, especially in
volatile markets, showing that spatio-temporal models can add predictive value in fluctuating
real estate markets.

These papers should offer insights into various algorithms, preprocessing techniques, and modeling
strategies you could apply or compare for your own house price prediction project.
Code and output:

You might also like