Sr. Associate, Advanced Analytics C00229

Solid background in Math, Statistics, and Finance. Experienced in data preparation, prediction, data visualization, and providing data-driven recommendations in the pharmaceutical industry

Industry and Project Experience

A pharmaceutical firm- Market Access

⦿ Develop a process to identify missing and problematic transactions submitted by Specialty Pharmacies, helped the client save $12 million
⦿ Conduct specialty pharmacy & practices cash vs commercial analysis, identify a high-value target and potential growth opportunity, product market share has increased 12.3% YOY
⦿ Perform copay analysis using Symphony claim data by looking at channel mix, medication protocol, and patient usage cycle, which conclude the client’s product patients out of pocket paid are on par with competitors, present the result to key stakeholders
⦿ Provide payer analytics/ Insights and ad-hoc support to the Market Access team and the Brand team. Proficient in IQVIA & Symphony Plantrak data, APLD, and MMIT formulary data

A pharmaceutical firm- Commercial Analytics

⦿ Conducted quantitative analyses on 10+ IMS datasets, designed and developed weekly KPI dashboard using SAS and Power BI to monitor performance across multiple areas of interest, extracted actionable business insights, led PRISM reporting platform launch
⦿ Developed IC payout process and created Business Rule document for a business unit; conducted analysis for identifying potential growth targets supported targeting and alignment process
⦿ Analyzed product source of business and patient journey by leveraging APLD data to establish regimen database, designed adherence, and persistence tracking report
⦿ Assessed the impact of experimental promotion on sales using statistical and descriptive methods to identify physicians with matching promotion and prescription behavior to create effective Test and Control groups, provided insights for executives’ decision making

Academic Projects

Applied Data Mining, Bethlehem, PA (Oct 2017 – Dec 2017)
Project Name: Wine Quality Classification

⦿ Preprocessed data by handling missing values, smoothing noisy data, and reducing dimensionality using SPSS on 7,000 entries, 12 attributes of red and white wine datasets
⦿ Applied neural network, CHAID decision tree, and C5.0 decision tree model, compared accuracy of my standard model with models created with boosting and bagging, concluded neural network is the best overall
⦿ Evaluated models by using gain charts, and determined the most important predictor variables are alcohol and volatile acidity

SAS Programming, Lehigh, Bethlehem, PA (Oct 2017 – Dec 2017)
Project Name: Stock Trading Framework

⦿ Implemented an artificial neural network (ANN) using SAS/IML to classify trading signals and generated effective trading decisions, retrieved data based on AAPL’s recent five years’ stock information including date, open, high, low, close, and volume using SQL
⦿ Calculated and analyzed the nonlinear relationship that exists among six popular technical indicators, applied extreme learning machine in SAS/IML using the first four years of data to train the ANN model
⦿ Tested the model with recent one-year AAPL stock price data and compared the model performance with other machine learning techniques such as the Decision Tree model and Support Vector Machine, outperforming by 13% on average in profit

Technical Skills

Education