Scribd Logo
Upload

Welcome to Scribd!

  • 4 views

    House Price Prediction

    Uploaded by

    prasadvdp74

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    House Price Prediction

    Uploaded by

    prasadvdp74
    4 views20 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    4 views20 pages

    House Price Prediction

    Uploaded by

    prasadvdp74

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 20

    SWARNANDHRA COLLEGE Of

    ENGINEERING &TECHNOLOGY
    (AUTONOMOUS)
    DEPARTMENT OF COMPUTER SCIENCE &
    ENGINEERING
    M.TECH MINI PROJECT REVIEW

    Under the Guidance of


    MR.P.Srinivasa Rao , M . Tech
    Associate professor
    Presented by
    HOUSE
    PRICE
    PREDICTIO
    N
    • abstract
    • Existing system
    • Proposed system
    • System specifications
    Contents: • Hardware and software requirements
    • Design and development
    • Implementation and output
    • Conclusion
    Real estate is a least transparent industry in
    our ecosystem.
    Housing prices keep changing day in and day
    out and sometimes are hyped rather than
    being based on valuation.
    Abstract: Predicating housing process with real factors is
    the main crux of our research project.here we
    aim to make our evaluations based on every
    basic parameter that is consider while
    determining the price.
    Data is the heart of the system of
    technical innovations, achieving any
    result is now possible using
    predictive models. Machine learning
    Existing is extensively used in this approach.
    system: Although development of correct
    and accurate model is needed.
    Previous algorithm like SVM are not
    suitable for complex real world data.
    Proposed system:
    • our main focus here is to develop a model which
    predicys the property cost based on vast datasets
    using data mining approach,
    • The data mining process in a real estate industry
    provides an advantage to the developers by
    processing the data.forecasting future trends and
    thus assisting them to make favourable
    knowledge driven descions.
    • Our dataset comprises of various essential
    parameters and data mining has been at the root
    of our system.
    • Finally a system will be made to predict the real
    estate prices using deep learning approach.
    System
    specifications:
    • Since this is AI based deep
    learning approach,we are
    going to use a dataset
    extracting the features of
    houses and algorithmic
    models to train the
    dataset for predictions.
    Data consists of more than 20000 records

    Around nine features provided in the dataset like latitude,total rooms


    etc.

    Data mining technique is used for processing of the dataset to extract


    relevant data to be future used in data models.

    Data models: the basic technique used for the model is regression
    analysis which is statistical method to model the relationship between
    a dependent (target) and independent (predictor) variables with one
    or more independent variables.it predicts continuous/real vvalues
    Hardware and software requirements
    Software requirements:
    • Python version-3.8
    • Libraries:
     Pandas
     Scikit-learn
     Matplotlib
     Seaborn
     Tensorflow
     Jupyterlab.
    • Hardware requirements:
     1.66 GHz Pentium processor or intel
    compatible processor.
     1GB RAM
     80 MB disk area.
    Design and
    development:
    • Since this project mainly
    integrates software rather
    hardware one,the emphasis
    is primarily on code
    development as follows:
    Step 1:
    • Import required libraries
    • Import data from dataset
    • Get some information from
    dataset
    Step 2:
    • Visualizing the data in terms of
    house
    process,affaordability.number of
    bedrooms etc.
    Step 3:
    • To display countplot() column
    Step 4:
    • Using info()
    Step 5:
    Detecting and removing outliers using
    ‘isolation forest algorithm’.
    Step 6:
    • Splitting into training and testing data:
    Implementation
    and output:
    • The final output or
    prediction is below as
    follows:
    • From the training and testing the dataset on
    the model a strong deduction can be made
    that the model ANN works most effectively
    Conclusion: on the data producing lower levels of errors,
    and hence we conclude that deep learning
    techniques prove useful in implementation
    and estimation of HOUSE PRICE PREDICTION.
    THANK
    YOU

    You might also like