Data Mining Neural Network for House Price Prediction
Download as PPTX, PDF0 likes11 views
This document discusses the application of neural networks in predicting house prices, detailing various types of neural networks such as feed-forward, recurrent, convolutional, and modular networks. It emphasizes the importance of data collection and preprocessing, and describes a specific project workflow including feature selection, model building, and evaluation. The project aims to leverage machine learning to accurately predict housing prices based on a variety of features and locations.
Data Mining Neural Network for House Price Prediction
- 1. Data Mining Neural Network for House Price Prediction Anand Kumar
- 2. DATA MINING THROUGH DIFFERENT TECHNIQUES
- 3. Introduction to Neural Network A neural network is a series of algorithms that endeavors to recognize underlying relationships in a set of data through a process that mimics the way the human brain operates.
- 4. Introduction to Neural Network Neural networks refer to systems of neurons, either organic or artificial in nature. Neural networks can adapt to changing input; so the network generates the best possible result without needing to redesign the output criteria. The concept of neural networks, which has its roots in artificial intelligence, is swiftly gaining popularity in the development of trading systems.
- 5. Types of Neural Network Feed-Forward Neural Networks • Feed-forward neural networks are one of the more simple types of neural networks. • It conveys information in one direction through input nodes; this information continues to be processed in this single direction until it reaches the output mode.
- 6. Types of Neural Network Recurrent Neural Networks • A more complex type of neural network, recurrent neural networks take the output of a processing node and transmit the information back into the network. • This results in theoretical "learning" and improvement of the network.
- 7. Types of Neural Network Convolutional Neural Networks • Convolutional neural networks, also called ConvNets or CNNs, have several layers in which data is sorted into categories. These networks have an input layer, an output layer, and a hidden multitude of convolutional layers in between. • The layers create feature maps that record areas of an image that are broken down further until they generate valuable outputs.
- 8. Types of Neural Network Modular Neural Networks • Modular neural networks contain several networks that work independently from one another. These networks do not interact with each other during an analysis process. • Instead, these processes are done to allow complex, elaborate computing processes to be done more efficiently.
- 9. Types of Neural Network Convolutional Neural Networks • Convolutional neural networks, also called ConvNets or CNNs, have several layers in which data is sorted into categories. These networks have an input layer, an output layer, and a hidden multitude of convolutional layers in between. • The layers create feature maps that record areas of an image that are broken down further until they generate valuable outputs.
- 10. How Can We Calculate House Price ● Prices of real estate properties are sophisticatedly linked with our economy. Despite this, we do not have accurate measures of housing prices based on the vast amount of data available. Therefore, the goal of this project is to use machine learning to predict the selling prices of houses based on many housing features and location. ● A house value is simply more than location and square footage. Like the features that make up a person, an educated party would want to know all aspects that give a house its value. ● We are going to take advantage of all of the feature variables available to use and use it to analyze and predict house prices.
- 11. Data Collection ● Dataset: housepricedata.csv (from Kaggle) ● Exploratory Data Analysis ● Geographical Properties ● Feature Engineering ● Scaling and Train Test Split ● Creating a model ● Training a model ● Evaluating on a test data ● Predicting a brand new house
- 12. Data Preprocessing • Data preprocessing steps required to prepare the data for modeling. • It Include tasks such as handling missing values, encoding categorical variables, and scaling numerical features. • In this project, missing value is handled by mean substitution, and duplicate values are basically dropped • Data normalization is not applicable here • Features selection is important, and it selects target variable.
- 13. Data Features • Lot Area (in sq ft) • Overall Quality (scale from 1 to 10) • Overall Condition (scale from 1 to 10) • Total Basement Area (in sq ft) • Number of Full Bathrooms • Number of Half Bathrooms • Number of Bedrooms above ground • Total Number of Rooms above ground • Number of Fireplaces • Garage Area (in sq ft)
- 14. Neural Network Architecture •Hidden layer 1: 32 neurons, ReLU activation •Hidden layer 2: 32 neurons, ReLU activation •Output Layer: 1 neuron, Sigmoid activation
- 15. Model Building • Read in the CSV (comma separated values) file and convert them to arrays. Arrays are a data format that our algorithm can process. • Split our dataset into the input features and the label • Scale the data so that the input features have similar orders of magnitude. • Split our dataset into the training set, the validation set and the test set. If you need a refresher on why we need these three datasets, please refer to
- 16. Model Building • X_train (10 input features, 70% of full dataset) • X_val (10 input features, 15% of full dataset) • X_test (10 input features, 15% of full dataset) • Y_train (1 label, 70% of full dataset) • Y_val (1 label, 15% of full dataset) • Y_test (1 label, 15% of full dataset) Entire dataset is fragmented into three sets training set, validating and testing set
- 17. Model Evaluation
- 18. Conclusion • Explore and Process the Data • Build and Train our Neural Network • Visualize Loss and Accuracy • Add Regularization to our Neural Network