Proven data scientist, with an expertise in automation and problem solving. Superb quantitative and qualitative analytical skills . Ability to apply programming, statistics, and data visualization to create actionable productional products. Excellent oral and written communication skills. Outstanding leadership, teamwork, and interpersonal relationships. Creative thinker
Microsoft Office Suite: Word, Excel, PowerPoint, Outlook, Access
- Implemented financial projection algorithm to predict company budget using python. Project will reduce human capital cost by 100’s of hours.
- Back tested models are projected to reduce yearly predicted error by 10%. Built using python module statsmodel, specifically using arimax models.
- Created employee attrition model using R. Created Random Forest and Neural Network using packages neuralnet, caret, and randomForest. ETL done using readr, dplyr, tidyr. Parrallelized using doParallel. Due to system constraints (Single Use CPU), this process was pushed into SAP PAL to handle higher dimensionality in training datasets. Was done to improve model training efficiency (1 - hour training period reduced to seconds using SAP environment).
- Transferred employee attrition model to SAP HANA using PAL. This resulted in a new Flight Risk Report indicating which employees may be ready to leave. Data Collection, ETL, Model Training, Predictions and Results is done using combination of SQL, xsjobs (cronjobs), XSJS, Angular, PAL(Predictive Analytics Library).
- Developed web app to create and generate predictive models: handling project creation, feature selection, algorithm selection and parameter setting, results, and validation. Built using AngularJS, Bootstrap and xsjs.
- Responsible for data acquisition through means of automated scripts, web scraping and api consumption.
- Capable of turning websites into actionable data. Resulted in over 500,000 new prospects. Python & R.
- Lead IT for benefits department. Created applications to communicate with third party sdks using SQL, Vb.net and vba, python and R.
- This created automation aimed to reduce data entry points. Reduced manual labor time of account managers by 10% weekly.
- Completely revamped data acquisition methods. Developed a distributed network of 48 AWS servers. Able to use hub servers to clone other servers to run web automated applications. AWS, R, PowerShell, python
- Create, document, and report on various operational functions, including store/employee performance, store optimization, etc. Excel, SQL
- Automation of excel reports, connecting workbooks to various databases to accomplish complete automation of reports. Excel, SQL
- Cultivated databases from web scraping to research MBA programs in the Northeast. R, PostgreSQL
- Built pricing analysis on book cost, tuition cost, semester courses, etc. R
- Create excel data scrapers, functions, macros to automate reports/ data analysis for risk assessment. Excel, VBA
- Active leader of the HERA process. Responsible for training employees in US, India and London. Process of liquidating assets in foreign currency, to USD to adhere to Dodd Frank laws.