Kushal Gowda's starred repositories
Bank-Loan-Default-Prediction
Predictive analytics encompasses a variety of statistical techniques from data mining, predictive modelling, and machine learning, that analyze current and historical facts to make predictions about future or otherwise unknown events. Loans default can act as detrimental for the bank causing huge losses so predictive modelling is tool that can be put to use in predicting behavior of the customers beforehand.
Lendingclub-loan
1 Introduction LendingClub is a peer to peer lending company in which their product allows consumers to both invest and borrow loans. They offer multiple kinds of loans like student loans, personal loans, auto refinancing loans and even business loans. The borrowers who are interested in obtaining loans will get a loan grade assigned to them which affect their interest rates and the amount of money they can borrow. A lot of the LendingClub data leads to insightful conclusions about the borrowing and investing patterns of all kinds of individuals. Through our investigation, we will explain patterns and similarities of the behaviors of borrowers and investors. 1.1 Questions of Interest We intend to start off with exploratory data analysis of all the factors involved to find patterns and relationships. We will look at the data from multiple angles to get a sense of the intricacies that lie within the data. We will additionally match the trend we see in the data to external events to try to explain why such is happening. We will also conduct time series decomposition in regards to the average loan amounts being requested. We will take a look at the trend and the seasonality so that we can better forecast spikes in demand. After, we will try to fit prediction models in order to answer a couple questions: namely whether a loan request from a client should be funded or not from the perspective of the bank, and what interest rate a borrower would get for a loan from the perspective of a client. After finding good models, we will deconstruct them in order to get a deeper sense of the important aspects in such decisions. 1.2 Dataset The dataset we are using is a compilation of data on loans issued by LendingClub from the period 2007 to 2015. The data includes information on the current loan status (how much has been funded so far, how much has been paid off, etc) as well as information about the borrower (occupation, income, credit score, etc). This data lends itself to a variety of interesting financial analysis, notably time series analysis since the data is date stamped. We will touch on a number of variables present in the dataset throughout the course of this analysis. We will consolidate the meanings of all these variables here for future reference. • loan_amnt: listed amount of the loan applied for by the borrower • funded_amnt: total amount committed to that loan at that point in time • funded_amnt_inv: total amount committed by investors for that loan at that point in time • term: number of payments on the loan. Values are in months and can be either 36 or 60 • int_rate: interest rate on the loan University of California, Davis • installment: monthly payment owed by the borrower • grade: loan grade that corresponds to the risk of the loan • loan_status: current status of the loan • total_bal_il: total current balance of all installment accounts • emp_title: job title of the borrower • next_pymnt_d: next scheduled payment date • sec_app_mort_acc: number of mortgage accounts at time of application for the secondary applicant More information about the dataset can be found here: https://www.kaggle.com/wendykan/lending-club-loan-data
Credit-Risk-Classification
Mortgages, student and auto loans, and debt consolidation are just a few examples of credit and loans that people seek online. Peer-to-peer lending services such as Loans Canada and Mogo let investors loan people money without using a bank. However, because investors always want to mitigate risk, it would be helpful to predict credit risk with machine learning techniques. This experiment attempts to predict credit risk based on various machine learning models, to find out the best performing model amongst them. Credit risk is inherently imbalanced classification problem (i.e., there will always be more number of good customers than the number of at-risk loans), so along with the exploratory analysis to understand the data and modeling for prediction, we need to balance the data before applying machine learning models. The following experiment presents the study on Credit risk and concentrates on, first on correct classification of Credit Risky customers. And second, more on reducing False Negatives, i.e., on reducing the classification error of classifying risky customers as non-risky.
Loan-Approval-Prediction
Unlock the power of machine learning for predicting loan approvals. This repository hosts code and resources to streamline the loan approval process. Data scientists and enthusiasts can leverage this open-source project to enhance credit risk assessment models. Clone, predict, and contribute to revolutionize the future of loan approval systems.
home-credit-default-risk
The dataset train.csv contains the some information about the loans; the source is Kaggle https://www.kaggle.com/c/home-credit-default-risk. The aim is to build a model that can predict the payment performance for the next loan requests, based on some predictors.
Forex-EUR-USD-App
Team project implementing Machine Learning to find arbitrage opportunities in the foreign exchange ('forex') rates between the USD and Euro. This was incorporated into a front-end package utilizing December, 2018 data for demonstration purposes.
Apple-website-webpage
Building with Backgrounds and Gradients [Solo Project] (Microverse curriculum)
Stanford-Project-Predicting-stock-prices-using-a-LSTM-Network
Stanford Project: Artificial Intelligence is changing virtually every aspect of our lives. Today’s algorithms accomplish tasks that until recently only expert humans could perform. As it relates to finance, this is an exciting time to adopt a disruptive technology that will transform how everyone invests for generations. Models that explain the returns of individual stocks generally use company and stock characteristics, e.g., the market prices of financial instruments and companies’ accounting data. These characteristics can also be used to predict expected stock returns out-of-sample. Most studies use simple linear models to form these predictions [1] or [2]. An increasing body of academic literature documents that more sophisticated tools from the Machine Learning (ML) and Deep Learning (DL) repertoire, which allow for nonlinear predictor interactions, can improve the stock return forecasts [3], [4] or [5]. The main goal of this project is to investigate whether modern DL techniques can be utilized to more efficiently predict the movements of the stock market. Specifically, we train a LSTM neural network with time series price-volume data and compare its out-of-sample return predictability with the performance of a simple logistic regression (our baseline model).
Deep_Learning_Machine_Learning_Stock
Deep Learning and Machine Learning stocks represent promising opportunities for both long-term and short-term investors and traders.
Stock-Prediction
Smart Algorithms to predict buying and selling of stocks on the basis of Mutual Funds Analysis, Stock Trends Analysis and Prediction, Portfolio Risk Factor, Stock and Finance Market News Sentiment Analysis and Selling profit ratio. Project developed as a part of NSE-FutureTech-Hackathon 2018, Mumbai. Team : Semicolon
Stock-Price-Prediction
A group project for CMPE272 at SJSU
interactive-tutorials
Interactive Tutorials