To calculate the default status of a customer and clean the data, you'll typically follow these steps:

1. Data Cleaning:

- Handle missing values: Replace missing values with appropriate measures such as mean, median,
or mode, or use imputation techniques.

- Correct data formats: Ensure all data types are correct and consistent across the dataset.

- Remove duplicates: Remove any duplicate entries to ensure data integrity.

- Standardize data: Convert categorical variables into a consistent format if necessary.

- Handle outliers: Identify and handle outliers that may skew the analysis or model.

2. Default Status Calculation:

- Define the criteria for default: Determine what constitutes a default event for your analysis. It
could be a missed payment, a certain number of days overdue, or another indicator.

- Calculate default status: Use historical data or predefined rules to determine whether each
customer has defaulted or not.

3. Merge Data:

- Merge default status with cleaned data: Once you have cleaned the data and calculated default
status, merge the two datasets using a unique identifier such as customer ID.

Here's a basic example in Python using pandas:

python

import pandas as pd

Load data

basic_details = pd.read_excel('basic_details.xlsx')

default_status = pd.read_excel('default_status.xlsx')

Data cleaning

(Assuming basic cleaning steps like handling missing values, correcting data formats, etc.)
Calculate default status (Assuming default_status is already calculated)

(For demonstration, assuming default_status contains 'Customer ID' and 'Default Status' columns)

Merge data

merged_data = [Link](basic_details, default_status, on='Customer ID', how='left')

Write merged data to a new Excel file or any desired format

merged_data.to_excel('merged_data.xlsx', index=False)

Now, let's delve into the literature survey on Credit Risk Modelling:

Literature Survey on Credit Risk Modelling:

Credit risk modelling is a crucial aspect of financial risk management, particularly for banks and
lending institutions. It involves assessing the likelihood of a borrower defaulting on a loan or credit
obligation. Over the years, various techniques and methodologies have been developed and refined
to address the challenges inherent in credit risk modelling. A comprehensive literature review reveals
several key themes and advancements in this field:

1. Traditional Approaches:

- Traditional credit risk models, such as the Credit Scoring Model and the Probability of Default (PD)
Model, have been extensively used in the industry.

- These models typically rely on historical data and statistical techniques to predict the likelihood of
default based on borrower characteristics, financial ratios, and credit history.

2. Machine Learning and Data-driven Approaches:

- With the advent of big data and advancements in machine learning algorithms, there has been a
paradigm shift towards data-driven credit risk modelling techniques.

- Machine learning models, including decision trees, random forests, support vector machines, and
neural networks, have shown promising results in predicting credit risk by leveraging large volumes
of structured and unstructured data.

3. Credit Scoring and Behavioral Modelling:

- Behavioral modelling techniques, such as survival analysis and hazard modelling, offer insights
into the dynamic nature of credit risk by considering the time-to-default and evolving borrower
behavior.

4. Risk Segmentation and Portfolio Management:

- Risk segmentation strategies, such as segmentation based on credit risk profiles or industry
sectors, help lenders tailor their risk management practices to different borrower segments.

- Portfolio management techniques, including diversification and risk-based pricing, enable

5. Regulatory Frameworks and Stress Testing:

- Regulatory frameworks, such as the Basel Accords, impose guidelines and standards for credit risk
management and capital adequacy requirements.

- Stress testing methodologies assess the resilience of financial institutions to adverse economic
scenarios and potential credit losses, providing insights into their overall risk exposure and capital
adequacy.

6. Emerging Trends and Challenges:

- Emerging trends in credit risk modelling include the integration of alternative data sources, such
as social media data and transactional data, to enhance predictive accuracy and risk assessment.

- Challenges in credit risk modelling encompass issues related to data quality, model
interpretability, and the dynamic nature of credit markets, highlighting the need for robust validation
frameworks and ongoing model monitoring.

In conclusion, credit risk modelling is a dynamic and evolving field that plays a critical role in
safeguarding the stability and solvency of financial institutions. By leveraging a combination of
traditional techniques and advanced analytics, practitioners can develop more accurate and robust
models for assessing credit risk and making informed lending decisions.