Synthesised loan risk database data on Loans to non-financial corporations includes loan amounts, maturities, and interest rates. To be accurate but not identify specific companies, the data was synthesised using specific software.

DESCRIPTION

Create a model that predicts whether or not a loan will be default using the historical data.

Problem Statement:

For companies like Lending Club correctly predicting whether or not a loan will be a default is very important. In this project, using the historical data from 2007 to 2015, you have to build a deep learning model to predict the chance of default for future loans. As you will see later this dataset is highly imbalanced and includes a lot of features that make this problem more challenging.

Domain: Finance

Analysis to be done: Perform data preprocessing and build a deep learning prediction model.

Content:

Dataset columns and definition:

credit.policy: 1 if the customer meets the credit underwriting criteria of LendingClub.com, and 0 otherwise.

purpose: The purpose of the loan (takes values "credit_card", "debt_consolidation", "educational", "major_purchase", "small_business", and "all_other").

int.rate: The interest rate of the loan, as a proportion (a rate of 11% would be stored as 0.11). Borrowers judged by LendingClub.com to be more risky are assigned higher interest rates.

installment: The monthly installments owed by the borrower if the loan is funded.

log.annual.inc: The natural log of the self-reported annual income of the borrower.

dti: The debt-to-income ratio of the borrower (amount of debt divided by annual income).

fico: The FICO credit score of the borrower.

days.with.cr.line: The number of days the borrower has had a credit line.

revol.bal: The borrower's revolving balance (amount unpaid at the end of the credit card billing cycle).

revol.util: The borrower's revolving line utilization rate (the amount of the credit line used relative to total credit available).

inq.last.6mths: The borrower's number of inquiries by creditors in the last 6 months.

delinq.2yrs: The number of times the borrower had been 30+ days past due on a payment in the past 2 years.

pub.rec: The borrower's number of derogatory public records (bankruptcy filings, tax liens, or judgments).

Steps to perform:

Perform exploratory data analysis and feature engineering and then apply feature engineering. Follow up with a deep learning model to predict whether or not the loan will be default using the historical data.

Tasks:

1. Feature Transformation

Transform categorical values into numerical values (discrete)

1. Exploratory data analysis of different factors of the dataset.

2. Additional Feature Engineering

You will check the correlation between features and will drop those features which have a strong correlation

This will help reduce the number of features and will leave you with the most relevant features

1. Modeling

After applying EDA and feature engineering, you are now ready to build the predictive models

In this part, you will create a deep learning model using Keras with Tensorflow backend

The National Student Loan Data System (NSLDS) is the national database of information about loans and grants awarded to students under Title IV of the Higher Education Act (HEA) of 1965. NSLDS provides a centralized, integrated view of Title IV loans and grants during their complete life cycle, from aid approval through disbursement, repayment, deferment, delinquency, and closure.

In 2023, the average auto loan debt in the United States was approximately 1,180 U.S. dollars higher than in the previous year. Overall, car loan debt of the average adult in the United States amounted to 23,792 U.S. dollars. The average size of car loans has increased every year since 2019.

USAID's Development Credit Authority (DCA) works with investors, local financial institutions, and development organizations to design and deliver investment alternatives that unlock financing for U.S. Government priorities. USAID guarantees encourage private lenders to extend financing to underserved borrowers in new sectors and regions. This dataset is the complete list of all private loans made under USAID's DCA since it was established in 1999. To protect the personal information of borrowers and bank partners, all strategic and personal identifiable information was removed.

In 2023, Wells Fargo had nearly 944 billion U.S. dollars in outstanding loans. The global outstanding loans of the bank, which has its headquarters in San Francisco, have fluctuated significantly in the past years. In fact, Wells Fargo had more loans outstanding in 2017 than in 2023. Despite that fall, Wells Fargo still was the bank with the third largest consumer loans portfolio in the U.S in 2022.

Individual car loan status statistical trend data (Financial Joint Credit Information Center)

These tables provide additional detail on the loan assets of U.S. depository institutions by reporting mortgage and consumer loan portfolios broken down by the banks' estimates of the probability of default, as defined below. This information facilitates analysis of the potential concentration of risk in specific loan categories. The institutions reporting this information are generally those with $10 billion or more of assets.

Locations and characteristics of projects that have received USDA Rural Development Community Facilities Loans, Grants, and Guaranteed Loans. Includes latitude and longitude coordinates, facility name and address, NAICS Code, funding type, obligation date and amount, total development cost, borrower name and type, and more

Statistics on the trend of loans for companies of various sizes (Financial Joint Credit Information System)

Provides information on repayment details by item and repayment details by maturity

This dataset is a modified version of the Kaggle Lending Club dataset found at https://www.kaggle.com/datasets/wordsforthewise/lending-club, including a model trained on the training set.

The data contains 2007 through 2018 Lending Club accepted and rejected loan data.

The dataset is licenced under CC0 1.0 Universal (CC0 1.0) Public Domain Dedication https://creativecommons.org/publicdomain/zero/1.0/

The International Bank for Reconstruction and Development (IBRD) loans are public and publicly guaranteed debt extended by the World Bank Group. IBRD loans are made to, or guaranteed by, countries that are members of IBRD. IBRD may also make loans to IFC. IBRD lends at market rates. Data are in U.S. dollars calculated using historical rates. This dataset contains historical snapshots of the Statement of Loans including the latest available snapshots. The World Bank complies with all sanctions applicable to World Bank transactions.

In 2023, BBVA concentrated roughly 24 percent of the loans granted in Mexico. BBVA had an even bigger market share in the mortgages segment. Meanwhile, Banorte's was the second organization in the ranking, with almost 15 percent of all lending. In 2024, Banorte ranked among the most valuable banking brands in Latin America.

Each report contains data for the relevant financial year as well as historical data. We currently have available:

HELP statistics, 2005–06 to 2023–24 financial years AASL statistics, 2014–15 to 2023–24 financial years VSL statistics, 2019–20 to 2023–24 financial years

Note that legislation is before parliament which may change the statistics for the 2023–24 income year. If the legislative change becomes law, these statistics will be updated.

All banks (including local and foreign banks' branches in Taiwan) extend credit to domestic private enterprises, government agencies, and individuals (or families), with credit limits specified, excluding underwriting of resold bills (bonds) and investments.

Abstract

The CoreLogic Loan-Level Market Analytics (LLMA) for primary mortgages dataset contains detailed loan data, including origination, events, performance, forbearance and inferred modification data.

Methodology

CoreLogic sources the Loan-Level Market Analytics data directly from loan servicers. CoreLogic cleans and augments the contributed records with modeled data. The Data Dictionary indicates which fields are contributed and which are inferred.

The Loan-Level Market Analytics data is aimed at providing lenders, servicers, investors, and advisory firms with the insights they need to make trustworthy assessments and accurate decisions. Stanford Libraries has purchased the Loan-Level Market Analytics data for researchers interested in housing, economics, finance and other topics related to prime and subprime first lien data.

CoreLogic provided the data to Stanford Libraries as pipe-delimited text files, which we have uploaded to Data Farm (Redivis) for preview, extraction and analysis.

For more information about how the data was prepared for Redivis, please see CoreLogic 2024 GitLab.

Usage

Per the End User License Agreement, the LLMA Data cannot be commingled (i.e. merged, mixed or combined) with Tax and Deed Data that Stanford University has licensed from CoreLogic, or other data which includes the same or similar data elements or that can otherwise be used to identify individual persons or loan servicers.

The 2015 major release of CoreLogic Loan-Level Market Analytics (for primary mortgages) was intended to enhance the CoreLogic servicing consortium through data quality improvements and integrated analytics. See **CL_LLMA_ReleaseNotes.pdf **for more information about these changes.

For more information about included variables, please see CL_LLMA_Data_Dictionary.pdf.

**

For more information about how the database was set up, please see LLMA_Download_Guide.pdf.

Bulk Data Access

Data access is required to view this section.

Loans to Private Sector in China increased to 834021.23 CNY Hundred Million in May from 833481.80 CNY Hundred Million in April of 2025. This dataset provides - China Loans To Private Sector - actual values, historical data, forecast, chart, statistics, economic calendar and news.

Most of the lending to individuals written-off by financial institutions in the United Kingdom (UK) in the last quarter of 2023 were unsecured loans. Mortgage write-offs only amounted to 27 million British pounds, a fraction of the values for credit cards and other personal loans. Nevertheless, the outstanding value of personal loans secured on dwellings was much higher than that of consumer credit.