SUMMARY

• Analytics Professional with M.S. in Applied Physics and 6+ years of experience in quantitative analysis and research, data mining, aggregation and validation, model development, scoring and validation of predictive models including financial time series models using Python, SAS, and R statistical computing software.
• Worked with datasets from various domains including Finance, Marketing, Pharmaceutical, and Manufacturing & Service Industries.
• Highly experienced in using the analytical and data visualization tools such as Python, R, SQL, SAS, MS Excel, MATLAB, QlikView, Tableau, Weka, C, and C++.
• Implemented advanced supervised and unsupervised learning methods of machine learning algorithm and statistical techniques like multivariate regression, Cluster analysis, Decision Trees, Monte Carlo simulation, Neural Nets, NLTP, k - means clustering, principal component analysis (PCA), regression and visualization techniques for pattern recognition or data mining and classification of feature vectors.
• Well experienced with ETL procedures and in handling large data sets. Excellent Visual representation of data and communicating analysis to all levels of business users within the organization.
• Data preparation for various statistical modeling, which includes data cleansing, descriptive statistics, missing data analysis, data validation and preliminary data reporting using Python (Pandas, numpy, scikit-learn, etc).
• Build classifier for feature vector through data extraction, model development, validation and scoring of predictive models. The validation of the model is conducted through Leave-One-Out-Cross validation (LOOC), k-fold cross validation or on a validation set.
• Conducts coding of qualitative variables and manipulation, complex hypothesis testing and statistical analysis through various statistical methodologies like experimental designs (ANOVA with or without replication, factorial design, ANCOVA, etc.), MANOVA, discriminant and factor analysis and statistical inferences in Python, and R computing environment.
• Performs Markov-Chain Monte-Carlo (MCMC) simulations like Gibbs Sampling, HM MCMC simulation of stock price volatilities and general Monte-Carlo simulation for density estimation and bootstrapping of parameters of financial time series models.
• Extensive knowledge in Software development life cycle (SDLC) methodologies like Waterfall Model, Agile Modeling and Rapid application development (RAD).

TECHNICAL SKILLS

Statistical Tools: Python (numpy, pandas, scikit-learn, scipy, matplotlib), R (ggplot2, randomForest, quantmod), SAS (BASE, MACRO, ODS, SQL, STAT, GRAPH), MATLAB, Weka, and MS Excelwith VBA.

Data Visualization tools: QlikView and Tableau

Relational Databases: Oracle 9i 10g 11g, MySQL, MS SQL Server 2014, and MS Access

Other languages and tools: Mathematica, C/C++, and GitHub.

Operating Systems: Windows 8/7, Mac, Linux, and UNIX.

Office Tools: MS Office 2013 (Access, Excel, Word, PowerPoint, Outlook), and MS Visio

PROFESSIONAL EXPERIENCE

Quantitative Analyst

Confidential, CA

Responsibilities:

• Investigated missing data and data anomalies inthe data sets.Imputed missing data with statistically probable values - through statistical analysis of the data distribution (without missing values).
• Manipulated large data sets (500+ million observations) and performed data validation and corrections, combined data from multiple tables (Python pandas and SQL).
• Created graphs and chart using Python (Matplotlib and Seaborn), and Tableau. Created permanent formattedclean data sets for present and future analysis, infilling several datasets and sorting and merging by common variables.Performed Ad hoc data analysis.
• Developed predictive models for the operating cost of various sectors and identified the means to reduce operating cost and maximize profits. Validated the models using k-fold cross validation strategies and AUC parameter. Employed feature engineering techniques in obtaining variables that better fits a model.
• Performed dimensionality reduction techniques such as PCA and ICA. Implemented Naïve Bayes, Monte Carlo, Markov Chain, linear regression, logistic regression, and Random forest and other ensemble methods in statistical modeling of the data.
• Developed final reports with graphs and charts to showcase the findings to the management.

Tools used: Python (sklearn, matplotlib, seaborn, pandas, numpy, scipy), SQL - (Oracle DB, Oracle SQL developer), MS Excel, Tableau, Git, GitHub, Windows, Mac

Confidential, OH

Statistical Analyst

Responsibilities:

• Worked as an R and Python programmer for marketing targeting solutions - fulfilment team.
• Coordinated processes related to marketing campaign eligibility. Participated in campaign setup team meetings. Prepared audit statistics on providers and policyholders using various fraud detection techniques. Developed a machine learning technique to detect anomalies in claims.
• Handled large data sets (200+ million observations), aggregated data from multiple tables (Python pandas and SQL), and performed data validation. Replaced the missing values using statistical analysis.
• Extracted and merged data from different sources like claims data mart and text files using Python and SQL. Performed data preparation and transformation using Python (pandas, numpy, scipy) to ensure data quality and consistency.
• Implemented predictive modelling techniques such as Boosted decision tree, logistic regression, MCMC, Naïve Bayes, SVM, k-NN, etc. to classify the data and predict the probability of faulty claims (anomalies).
• Generated reports using R and Python and analysed on aggregate claims statistics such as total amount billed, per-subject billing amounts etc. for auditors and investigators.
• Conducted analysis on client consumer databases looking at profitability, transaction behavior, and demographic characteristics. Provided segmentation for database marketing efforts, such as CHAID, cluster analysis, and customer profiling.

Tools used: Python (sklearn, matplotlib, pandas, numpy, scipy), R (ggplot2), SQL - (Oracle DB, Oracle SQL developer), MS Excel with VBA, Windows, Linux

Confidential

Data Analyst

Responsibilities:

• Combined data from many tables using SQL and transformed it.
• Performed statistical analysis on the data for demographic spread of the customers and identified the possible locations for new branch.
• Analyzed the performance of the employees based on the projects, impact score, role, experience, etc. and determined the salary raise factor for the next year.
• Performed Ad hoc statistical analysis and reporting of the results.
• Interacted with other team members and lead to discuss the required developments to be made in coding to improve the functionality and effectiveness.
• Generated analysis reports, graphs using R and MS Excel.

Tools used: R, MS Excel, SQL (MS Visual studio 2007), MS Access.