SHUBHAM KOTAL

Model Validation | Risk Analytics. Ensuring model input and output are both clean, handling data quality issues, missing inputs. Testing the model expectations while verifying the model implementation. Model performance evaluation, comparing to alternatives so called benchmark model in order to analyze the impact of changing model assumptions by examining the model's stability and the robustness of the testing process. Revalidation : ABS Auto Spread (Portfolio Valuation). Predict ABS Auto Spread under the different macroeconomic scenarios. It's a CCAR process. Selection of macroeconomic input variable, performing EDA, normality test, variable stationarity test, correlation test, model selection, model validation and testing, metric calculation using RMSE and R-square, residual analysis. Tool: SAS, Model: Linear Regression.

Automating trading strategies using python. Creating scanners, backtesting, broker API integration, and cloud deployment of profitable trading strategies using technical and quantitative methods.

Model Development, Validation and Metric calculation. Worked on various product portfolios such as personal loans, credit cards, and home loans. Developed & validated quantitative models such as the probability of default (PD), exposure at default (EAD) & loss given default (LGD) for assessing the risk involved in giving loans. Credit Risk Modelling - Deciding whether to give a loan or not, also getting the probability of customer fraud. Created a probability of default (PD) model using logistic regression ML technique with python. Also did model validation & metric calculation with confusion matrix, Recall, Precision, AUC ROC, GINI, KS.

Specialization in Credit and Market Risk using ML, DL and Quantitative Models such Regression Models, CAPM, Binomial Models, Time Series Models ARMA, VAR, Monte Carlo, Put Call Parity and Black Scholes.

Specialization in Machine Learning and Deep Learning. Learned algorithms such as Linear Regression, Logistic Regression, Decision Tree, Random Forest, SVM, XG-Boost, KNN, RNN, and LSTM.