Repository containing portfolio of data science projects completed by me for academic, self learning, and practice purposes. Presented in the form of iPython Notebooks, and R markdown files.
For a more visually pleasant experience for browsing the portfolio, check out https://uk48762.wixsite.com/kushwaha
For well explanantion of projects done in R Studio, i have done those with the help of Kaggle R-Kernel to show input and output at same place for better understanding.
Link:https://www.kaggle.com/imkushwaha/project-property-price-prediction
Link:https://www.kaggle.com/imkushwaha/project-bank-credit-card-default-prediction
Link:https://www.kaggle.com/imkushwaha/project-wine-classification
Link:https://www.kaggle.com/imkushwaha/project-churn-analysis-in-telecom-industry
A model to predict the price of the property from the dataset having attributes such as sale type, sale condition etc. Identified the best price that a client can sell their house utilizing machine learning.
A classification model using logistic regression to predict the credibility of the customer, in order to minimize the risk and maximize the profit of German Credit Bank.
A classification model using linear discriminant analysis to classify the wine category from a data set, Which are the results of a chemical analysis of wines grown in the same region in Italy but derived from three different cultivars.
A classification models using decision tree algorithm to predict whether the customer be churned or not on the basis of its billing information and customer demographics.
Time Series (ARIMA) to build model to predict and forecast the sales of furniture for the next one year i.e. predict future values based on previously observed values. We have a 4-year furniture sales data.
K-means clustering model to classify the interest of teenagers by using various attributes.
Using principal component analysis, to reduce the data dimensions for the housing data attributes.
A a linear regression model with stochastic gradient descent to predict the price of the property from the dataset having attributes such as sale type, sale condition etc.
A classification model using logistic regression with stochastic gradient descent to predict the credibility of the customer, in order to minimize the risk and maximize the profit of a bank.
A predictive model using machine learning algorithms(K Nearest Neighbor) to predict whether the tumor is benign or malignant.
Decision Tree, Random Forest/XGBoost/Adaboost models to predict if the client will subscribe to a term deposit.
A classification model using support vector classifier to predict the credibility of the customer, in order to minimize the risk and maximize the profit of a bank.
Tools: scikit-learn, Pandas, Seaborn, Matplotlib, Numpy and many more.
If you liked what you saw, want to have a chat with me about the portfolio, work opportunities, or collaboration, shoot an email at upendra.kumar48762@gmail.com