Data Analyst

Siddharth Paryani https://www.linkedin.com/in/siddharth-paryani https://github.com/isidparyani

*** * *** ******, **** 302, Tempe, AZ, 85281 480-***-**** ********@***.***

Summary

Graduate Business Analytics student around two years of experience, having strong communication and problem-solving skills. Looking for an opportunity as a Business Analyst or Data Analyst.

Education

W. P. Carey School of Business at Arizona State University, Tempe, AZ May 2018

Master of Science in Business Analytics (MSBA), CGPA: 3.83

Visvesvaraya National Institute of Technology Nagpur, India Dec 2014

Bachelor of Technology in Computer Science

Professional Skills

Programming and Database Skills: R, Python (Pandas, NumPy, Sci-Kit Learn, SciPy, Matplotlib) SQL, ETL Technologies, Data Warehousing, Data Visualization, RDBMS, C, C++.

Data Mining and Machine Learning Algorithms: Classification Techniques, Decision Trees, Random Forests, Logistic Regression, Naïve Bayes Classifier, SVM, KNN, Clustering Techniques, K- Means, Kohonen Networks, Neural Networks, Recommendation Systems.

Data Analytic Tools: MySQL Workbench, R Studio, Anaconda, Spyder, Microsoft Azure ML, Minitab, Microsoft Excel, Stat Tools, SPSS Modeler, Precision Tree, @Risk, SAS, Amazon Web Services.

Data Visualization and Presentation Tools: Tableau, Power BI, IBM Watson Analytics.

Statistical Knowledge and Skills: Exploratory Data Analysis, Hypothesis Testing, Regression Analysis, Time Series and Forecasting Analysis, Data Modelling, Linear Algebra, Factor Analysis, Principal Component Analysis, A/B testing, ANOVA, Design of Experiment, Exponential Smoothing.

Analytic Projects

Churn Prediction: Supervised Machine Learning

W.P Carey School of Business, Arizona State University

Built a classification model to identify customers who are likely to churn, using Azure ML.

Used various techniques for Feature Selection such as Pearson’s Correlation, Kendall Karson.

Used Feature Engineering to transform the raw data into features for the predictive model to understand.

Used numerous Classification Techniques such as Decision Trees and Random Forests, achieving a Recall of 93%.

Insurance Purchase Likelihood: Supervised Machine Learning

W.P Carey School of Business, Arizona State University

Developed a classification model for predicting which customers are likely to purchase an insurance.

Overcame challenges of imbalanced data by using SMOTE and under sampling techniques.

Compared different classification techniques to compare which model performed the best.

Used Cross Validation techniques.

Used Ensemble Methods from various algorithms for minimizing error rates and achieving an accuracy of 87%.

Marketing Term Deposit: Supervised Machine Learning

W.P Carey School of Business, Arizona State University

Built various classification models for predicting which customers are likely to go for a term deposit.

Performed exploratory data analysis on the dataset.

Handled imbalanced data by using under sampling and oversampling techniques.

Used Logistic Regression to identify variables which were contributing the most for prediction.

Used various classification techniques such as SVM, Decision Trees, Random Forest using R, achieving a Recall of 99.8%.

Experience

Data Analyst Intern Jan 2018 – Apr 2018

Find your Influence, Tempe, Arizona

Built a Recommendation system to provide positive influencers (influential people) for advertisers to promote and market their brands through campaigns by finding similar influencers who work in similar advertiser categories using clustering techniques such as Kmeans.

Used various Data Transformation techniques.

Provided the client with valuable insights with the aid of Tableau and Power BI.

Built a Logistic Regression model to predict and identify which inexperienced influencer would be a potential candidate for an advertiser.

Analyst Jan 2016 – Jun 2017

Al Jazeera Computers, Abu Dhabi, UAE

Used models with classification techniques such as Decision Trees, Random Forests and SVM, to assist the company in recognizing clients, who would be inclined towards purchasing annual maintenance contracts for IT services. This also helped increase the company’s revenue by 15%.

Forecasted sales for the company using various Exponential Smoothing models.

Used Minitab to analyze and interpret trends and seasonal patterns of the company’s sales over the years.

Manipulated and merged data columns from multiple data sources using MySQL, for data analysis and used multi-dimensional data models for reporting.

Identified key factors responsible for the company’s revenue analysis.

In Python prepared data, did preprocessing for implementation of classification techniques.

Worked extensively with Tableau for presenting monthly reports and insights to senior managers, decision makers and stakeholders.

Contact this candidate