Senior Data Scientist Resume
MA
SUMMARY:
- Overall 15 years of experience as business analytics/data Science professional in predictive analytics and project management across aviation, logistics & transportation and healthcare industries.
- Analytics and business Intelligence leader with a strategic focus on providing data - driven insights and end-to-end solutions to business problems.
- Proven experience in preparing and presenting performance dashboards to top level executives of organization
- Proven experience in leading cross functional teams to lead business improvement/IT projects at Confidential group to improve productivity and service levels.
- Led business support team of 6 Industrial engineers at Confidential group and was responsible for annual planning and budgeting for ground handling division.
- Business analytics professional who can not only talk to business leaders to understand their requirement but also can handle big data and develop predictive models in Python and R.
- Machine learning expert with experience in developing predictive models to solve business problems with 3 years of experience in hands on coding and developing predictive models..
- Proficient in using Python, R, SQL, Hadoop ecosystem for extracting data and building predictive models.
- Very good knowledge in various statistical methods like time series analysis, statistical testing, multivariate analysis.
- Quick learner of various new technical concepts in machine learning/deep learning field.
TECHNICAL SKILLS:
Machine Learning: Linear/Logistic /Quantile Regression, Classification and Regression Trees (CART), Support Vector Machine, Random Forest, Gradient Boosting Machine (GBM), XGBoost
Statistics: Time Series (ARIMA) analysis, Principal Component Analysis(PCA)
Deep Learning: TensorFlow, Keras
Programming & Software: Python, R, h2o, SAS Enterprise Guide
Big Data skills: , Hadoop, Pig, Hive, Talend
Data visualization: Tableau, d3.js
PROFESSIONAL EXPERIENCE:
Confidential, MA
Senior Data Scientist
Responsibilities:
- Led and architected the entire ETL, data pipelines and machine learning model framework consisting of quantile regression and random forest.
- Presented results to vice president and above levels.
- Liaised with data engineering team to productionalize the model.
- Led the efforts to test ETL, data pipeline and Model testing/evaluation pipeline and productionalized 4 ML models so far.
Tools: used - R, Hive, h2o, git lab (version control)
Confidential, FL
Manager Operations Research & Data Mining
Responsibilities:
- To identify whether whistle post exists in an image or not using deep learning (object identification).
- To predict whether a locomotive requires wheel machining or not, so that it can be directed to a workshop which has wheel machining facilities.
- To predict whether a locomotive has mechanical problem from wayside sensor data.
- To predict number of wooden ties deteriorated across Confidential network in United States.
Tool: used - Python (Pandas,TensorFlow, opencv), AWS, R (Caret,ctree, randomForest, XGBoost), SQL
Confidential, CA
Data Scientist (Intern)
Responsibilities:
- To predict number of Confidential viewers during the first week after a video upload.
- To provide forecast for 8th,9th and 10th day using number of viewers for first week
Confidential, CA
Data Scientist (Intern)
Responsibilities:
- To identify similar part descriptions across 5 M parts in oil & rig designs
- To identify best payment terms for various Confidential businesses.