House Price Prediction for Ai & ml project .pptx

AI & Ml

1. House Price Prediction 3 rd Semester MIni -project Submitted By: Aditi Chauhan Mentored By: Dr. Vikas Tripathi

2. Student details - name : Aditi Chauhan university Roll NO. : 2019404 Section : Ai & ds

3. introduction House price estimation is an essential topic of real estate and its value ranges are a big issue for clients and real estate agents. Every year, rising housing prices, emphasize the necessity for a strategy or technique that can predict future house values. House prices are influenced by a variety of factors i.e. physical qualities, location, and the number of rooms. These factors have conventionally been used to make predictions.

4. Problem Statement Buyers are generally not aware of the factors that influence the house prices and get fooled easily . Also many problems are faced during purchase of property and as technology is increasing and manual house purchasing methods are being untrustworthy. To overcome such problems, we decided to create a housing price predicting model in the present work which enables the buyer and seller to anticipate the price of house.

5. methodology Before going into the methodology, understanding the problem is much more important. The problem is creating the hypothesis function that may give the prediction of the target value based on the data given as the training part. Then see or analyze the prediction on the testing part of the data. Here the data given is on the house price and its respective features which accommodate the price of the house. Thus, to build the machine to learn the data features and predict the price accurately is a challenging task. This will also help society of the real estate builder to easily predict the price of the land, house, etc. according to their feature with the help of this model. The dataset for this is taken from Kaggle’s Housing Data Set Knowledge Competition. Data set is simple and this aims at the prediction of the house price in Bengaluru, India. Thus, the data has been downloaded from the Kaggle Housing Datasets.

6. W hen the machine will predict the price it will get matched with the actual value and the mean error will get calculated which will give the accuracy rate of the model. The dataset may contain the various detailed features of the houses. Now import the data set with the help of the pandas in python platform and analyze the data set. Check all the features of the house related to the dependent target. Analyze and visualize the data by checking the missing values, fill all the missing values by taking the median of all the values of that attribute. Change the data which are uncategorical form, place the one hot encoder, for changing the categorical data into the numerical data. Change the entire alphabet values of the attribute into the numerical values. Select the most nearly features on which the labeled target is truly dependent. Before applying the machine learning regression function to the data, split the data into two parts one is training data and another is testing data. Apply machine learning on the training part of the data by the help of sklearn library in python platform. The detail explanation of the data flow diagram is as follows. The fetching operation is done with the help of the pandas library function in the format of .csv file and giving the path where data is stored .

7. Flow Of Project

8. Tkinter gui Python has many GUI frameworks, however, the most effective, Tkinter is constructed into the Python well-known library. Tkinter has some strengths. It is a go-platform, so the same code works on Windows, macOS, and Linux. Visual elements are rendered using local operating device factors. H owever, a terrific criticism is that GUIs were built with Tkinter appearance previously. In case you need a shiny, contemporary consumer interface, Tkinter won't be what you are searching for. However, Tkinter is lightweight and relatively easy to apply compared to other Frameworks. This is an appealing the choice for constructing GUI applications in Python.

9. Result & Conclusion CONCLUSION : The goal was to achieve a system that will reduce the human effort to find a house having a reasonable price. Hence t he proposed system, the House Price Prediction model approximately tries to achieve the same. A proposed system focused on predicting the house price according to the provided information processing and machine learning methods are used. Overall, the results give with practical information regarding the cause of various features on house prices and their corresponding analysis. The developed model may work efficiently and fulfill the needs of the buyer and seller of the house, and the property and user interface are very easy to use for everyone. A system that aims to provide an accurate prediction of housing prices has been developed, preventing the risk of investing in the wrong house. Additional features for the customer’s benefit can also be added to the system without disturbing its core functionality. A major future update could be the addition of larger cities to the database, which will allow our users to explore more houses, get more accuracy and thus come to a proper decision.

10. RESULT :

11. FUTURE SCOPE The accuracy of the system can be improved. Several more sites can be included in the system if the size and computational power increases of the system. Furthermore, we can integrate different UI/UX methodologies for better visualization of the results in a more interactive way using Augmented Reality. Also, a learning system can be Created which will gather the user’s feedback and history so that the system can display the most suitable Results to the user according to his preferences. In the future, we can present a comparative study of the systems’ predicted price and the price from real estate websites Such as Housing.com for the same user input. Also, to simplify it for the user, we are going to recommend a real estate Properties to the user, based on the predicted price. To make the system even more informative and user-friendly, we can Include G-map. This will show the neighborhood conveniences such as hospitals, and schools surrounding a region of 1 km from the given location. This can also be included in making predictions since the presence of such factors increases the valuation of real estate property.