Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 10

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

(MCA PROGRAMME)

PRESENTATION
ON
[SYNOPSIS]
Prediction of Loan Pricing on the basis of Area
Location using Machine Learning Algorithms
SUBMITTED BY
NAME : ABHISHEK
USN : 2VX22MC001

INTERNAL GUIDE
DR. M. N. BIRJE

PROF, DEPT. OF CSE


INTRODUCTION
The objective of this project is to develop a predictive model
for loan pricing based on the geographical location of
properties. By leveraging machine learning techniques, the
project aims to analyze various factors associated with different
areas, such as average property values, local economic
conditions, and historical loan performance data.
LITERATURE SURVEY
Existing System :
To showcase the use of an existing machine learning system to predict loan
pricing based on area location.

Loan prices vary by location due to differences in property values,


economic conditions, and demand
Proposed System :

The proposed method is to build a ML model to detect the insects of loan


pricing on area location

1 Approach: Use machine learning algorithms to analyze area-

specific data and predict loan prices.

2 Benefits: Improved accuracy in pricing, better risk


management, and enhanced customer satisfaction.

 Data Collection

Data Sources: Real estate databases, financial records,


public datasets, government reports.
 Types of Data:
1. Property values
2. Local economic indicators
(income levels, employment rates)
3. Historical loan prices
4.Demographic information
 Data Preprocessing:
Data Cleaning: Handle missing values, outliers, and
inconsistencies.
Methods: Correlation analysis, feature importance ranking
(using tree-based methods).
Key Features :
1. Property value
2. Average income in the area
3. Unemployment rate
4. Historical loan prices
METHODOLOGY CHOSEN
 Step1: Importing the libraries such as numpy, pandas,
seaborn, etc.

 Step2: Read the data from the dataset. Which is used to know
about the whole structure of the dataset.

 Step3: Splitting Data. In which Training and Testing data are


splitting.

 Step4: Building the models.(decision Tree, SVM)

 Step5: Calculating classification report. Which gives accuracy


of the model while preprocessing the data.
Hardware and Software Requirements
Hardware Requirements:

Computer : 1 GHz minimum, multi-core processor

Memory (RAM) : At least 512 KB


Hard disk space : At least 1 GB
Software Requirements:

 Operating System : Windows XP and above.

 Server side Script : Python, Anaconda

 Programming Language : Python, Machine Learning (ML).

 Libraries Used : Sklearn , pandas, TensorFlow,


numpy .

 Technology : Python 3.6


CONCLUSION
Predicting loan prices based on area location using machine
learning involves developing a model that can accurately assess
the value of loans by analyzing various location-specific factors.
The project begins with data collection, gathering relevant
information such as historical loan prices, geographical data,
property values, local economic indicators, and other socio-
economic factors.

You might also like