2022 V13i1198
2022 V13i1198
2022 V13i1198
project aims to provide a loan [1, 8] to a deserving applicant out of all applicants. An efficient
and non-biased system that reduces the bank’s time employs checking every applicant on a
priority basis. The bank authorities complete all other customer’s other formalities on time,
which positively impacts the customers. The best part is that it is efficient for both banks and
applicants.
As the data are increasing daily due to digitization in the banking sector, people want to apply
for loans through the internet. Artificial intelligence (AI), as a typical method for information
investigation, has gotten more consideration increasingly. Individuals of various businesses
are utilizing AI calculations to take care of the issues dependent on their industry
information. Banks are facing a significant problem in the approval of the loan. Daily there
are so many applications that are challenging to manage by the bank employees, and the
chances of some mistakes are high. Most banks earn profit from the loan, but it is risky to
choose deserving customers from the number of applications. One mistake can make a
massive loss to a bank.
Loan distribution is the primary business of almost every bank. This project aims to provide a
loan [1, 2] to a deserving applicant out of all applicants. An efficient and non-biased system
that reduces the bank’s time employs checking every applicant on a priority basis. The bank
authorities complete all other customer’s other formalities on time, which positively impacts
the customers. The best part is that it is efficient for both banks and applicants. This system
allows jumping on applications that deserve to be approved on a priority basis.
2. LITERATURE SURVEY
Sheikh et al. studied a very important approach in predictive analytics is used to study the
problem of predicting loan defaulters: The Logistic regression model. The data is collected
from the Kaggle for studying and prediction. Logistic Regression models have been
performed and the different measures of performances are computed. The models are
compared since the performance measures such as sensitivity and specificity.
Tumuluru et al. used the Machine Learning (ML) algorithms to extract patterns from a
common loan-approved dataset and retrieve patterns in forecasting future loan defaulters.
Customers’ past data, such as their age, income, loan amount, and tenure of work, will be
used to conduct the analysis. To determine the maximum relevant features, i.e., the factors
that have the most impact on the prediction outcome, various ML algorithms such as Random
Forest, Support Vector Machine, K-Nearest Neighbor and Logistic Regression, were used.
These mentioned algorithms are evaluated with the standard metrics and compared with each
other. The random forest algorithm achieves better accuracy.
Lohani et al. aimed to minimize the credit risks of defaulting. This study has applied logistic
regression as a tool to predict whether an applicant is eligible for the loan or not. The data is
collected from the Kaggle for studying and prediction.
Shaheen et al. applied on different machine learning techniques on customer's loans dataset
obtained from a public bank's database that contains customer's loans and personal data. The
data is processed and analyzed using Apache Spark, a machine learning tool for big data
processing. The result of the proposed system is evaluated by seven performance metrics to
compare the performance of each classifier and find out the best performing one among them.
It is found out that the ensemble machine learning techniques has better performance than
single base classifiers in predicting the loan default.
Sharma et al. studied the learning techniques as well as the raw datasets utilized for training
and test sets. The system model’s precision is also discussed. This work also provides a quick
overview of a few datasets that can be used to anticipate loan/mortgage analysis. Recent and
future trends are also spotlighted.
Gupta et al. used a machine learning technique that will predict the person who is reliable for
a loan, based on the previous record of the person whom the loan amount is accredited
before. This work's primary objective is to predict whether the loan approval to a specific
individual is safe or not.
Maheswari et al. used statistical measures to preprocess the data and build an effective model
that will predicts the loan defaulter accurately.
Lai et al. demonstrated that the AdaBoost model can achieve a 100% accuracy for predicting
loan default, outperforming other models including XGBoost, random forest, k nearest
neighbors, and multilayer perceptrons. This result showed the promising application of
machine learning techniques in the financial industry.
Ereiz et al. demonstrated the prediction using machine learning models is very high but
depends on the quality of the data. Several algorithms (to be more specific - BigML's
OptiML) were used to identify the best suited for the lending business.
Kumar et al. reduced the risking factor of banks behind finding the appropriate person for
loan approval by the bank. This work even reduced the time of loan approval analysis. This
work first used data mining techniques to analyze previous records to which the bank has
already sanctioned loan based on the analysis made out of these records this work train the
deep learning model. The new data is treated as testing data, and the output of the customer is
calculated accordingly.
3. PROPOSED SYSTEM
Fig. 1 shows the proposed block diagram of loan description.
Applications
Face recognition
Weather prediction
Medical diagnosis
Spam detection
Age/gender identification
Language identification
Sentimental analysis
Authorship identification
News classification