Python Data

Karthik Reddy

Bergen Ave, Kearny, NJ *****

B ***********@*******.*** B https://www.linkedin.com/in/karthik-reddy-588614177/ H +1-201-***-**** EDUCATION

New Jersey Institute Of Technology — Ying Wu College Of Computing, Newark, NJ Master of Science, Information Systems Sep. 2018 – May. 2020 Coursework And Mooc’s: Machine Learning, Deep Learning, Data Analysis, Web Mining, Database Systems, Statistics Sreenidhi Institute Of Science And Technology, Hyderabad, Telangana, India Bachelors of Technology in Mechanical Engineering Aug. 2013 – Apr. 2017 WORK EXPERIENCE

UBER, Hyderabad, India

Data Science Analyst Jun. 2017 – Aug. 2018

Used Pandas, NumPy, SciPy, Matplotlib, Scikit-learn, NLTK in Python for developing various machine learning algorithms and utilized algorithms such as XGBoost, Logistic Regression, Random Forests, KNN for predicting employee attrition

Built Data Pipelines in Python for comparing the classification models to predict the model with the best score

Participated in all phases of data mining; data collection, data cleaning, developing models, validation and visualization

Created reports and dashboards using Tableau and Excel to communicate employee performances to the Senior Manager DATA SCIENCE PROJECTS

Credit Card Fraud Detection Using Machine Learning Project Github Link Nov. 2019 – Jan. 2020

Built a Machine Learning Classifier in Python to detect whether a transaction is a normal payment or fraud

Anomaly Detection: Removed extreme outliers from features that have a high correlation with our class

Classifiers: Obtained the parameters that give the best predictive score for predictive models using GridSearchCV

Among the predictive models, Logistic Regression Classifier shows the best score in both training and validation sets

Python - (Keras, NumPy, Pandas, Scikit-learn, Seaborn), Algorithms - (Decision Tree, Support Vector Classifier, KNN, Neural Networks)

Predicting Term Deposit Subscription Of Banks

Project Github Link Aug. 2019 – Oct. 2019

Identified whether or not a potential client will subscribe to a term deposit or not

Built data pipelines to preprocess the data, used cross-validation to avoid overfitting

Used various classifiers, implemented ROC curves and found that Gradient Boosting classifier is the best model to predict whether a potential client will subscribe to a term deposit or not

Python - (Pandas, Scikit-Learn, Matplotlib, Seaborn), Algorithms - (Gradient Boosting, Decision Tree, Random Forest, KNeighbours Classifier)

Who’s Tweeting? Trump or Trudeau? (Tweet Classification Using NLP) Project Github Link May. 2019 – Jul. 2019

Built a Machine Learning Classifier that identifies whether President Trump or Prime Minister Justin Trudeau is tweeting!

Used CountVectorizer, TfidfVectorizer classes to create a vectorized representation of the tweets by Trump and Trudeau

Trained Linear SVC model over TF-IDF vectorized tweets and observed an increase in the accuracy of the model

Python - (NumPy, Pandas, Scikit-Learn), Algorithms - (Naive Bayes, Linear Support Vector Classifier) Airbnb: The Amsterdam Story With Interactive Maps

Project Github Link Mar. 2019 – Apr. 2019

Obtained an inside Airbnb listing data for Amsterdam and analysed the popular trends and predicted Amsterdam’s listing prices. The peak average price of listing was 240 Euros

De Baarsjes (3300) and South Of De Pijp(2400) were the top 2 neighbours with the most listing

Centrum West(172 Euros) and Centrum Oost(154 Euros) were the most expensive neighbourhoods

Python - (NLTK, NumPy, Pandas, GeoPandas, Matplotlib, Plotly, Folium) IMDB Movie Recommender Engine

Project Github Link Jan. 2019 – Feb. 2019

Used weighted average IMDB formula as a metric to scale the rating, plotted the best movies based on the scaled metric

Built a movie recommender system that shares movies with similar plot summaries using TF-IDF

Computed the Sigmoid Kernel to calculate the numerical quantity that denotes the similarity between two movies

Python - (NumPy, Pandas, Scikit-Learn, Matplotlib, Seaborn) SKILLS & OTHERS

Machine Learning: Algorithms - Decision Tree, Random Forest, Naive Bayes, Gradient Boosting, Support Vector Classifier, KNN, Linear Regression, Logistic Regression, Neural Networks, Recommender Systems and A/B tests Programming Languages: Python - (NumPy, Pandas, Scikit-Learn, Matplotlib, Seaborn), SQL Data Visualization Tools: Tableau, Matplotlib, Seaborn, Excel Database Softwares: Microsoft SQL Server, MySQL, MongoDB

Contact this candidate