Education
B.Tech/B.E. (COLLEGE OF ENGINEERING, PUNE (COE), Pune - 2003)
Experience
Professional Summary:
Has 15 Years of rich experience spanning across multiple types of industries, domains and technologies. An extremely adept Data Scientist and an astute Program Manager, has worked on several end-to-end Data Science projects and has managed several Projects and Programs.
o Certifications - Obtained Data Science Certifications from two premier institutes â
⣠Indian Institute of Management Bangalore (IIMB)
⣠Johns Hopkins University
⣠Obtained PMP Certification from Project Management Institute
⣠Obtained Certification on Operations Management from University of Pennsylvania
o Data Mining â Extensive experience in:
⣠Retrieving data from various databases â Structured (SAP / HANA / Oracle / SQL) as well as un-Structured (MongoDB) and Big Data Platforms (Hadoop).
⣠Writing online scripts as well as scheduling back-end jobs
⣠Creating ETL packages â SSIS / Spoon / Airflow
o Data Wrangling â High level of proficiency in Data Wrangling techniques that involve (but not limited to):
⣠Dealing with incorrect/missing data points (imputation techniques)
⣠Treatment of Influential Outliers (Cooks Distance and Box-Plot techniques) and High Leverage Data Points (using Hat Values) for univariate and multivariate data
⣠Checking for Multi-Collinearity and Heteroscedasticity
⣠Dimension Reduction techniques â Principle Components Analysis (PCA) and Linear Discriminant Analysis (LDA)
⣠Feature Selection Techniques: Variables used to split data at Nodes belonging to the first few layers of Decision Tree, Contribution of Variables to PCA, Inter-Correlation of Variables etc.
⣠Treating Imbalanced Data set â Over/Under sampling techniques, Cluster Sampling, SMOT, MSMOT and SMOTBoost.
⣠Feature Transformation: Mean Scaling, Normalization, Log, Box-Cox Transformation etc.
⣠Usage of R Packages â dplyr, tidyr, lubridate, data.table, reshape2 etc.
o Descriptive Analytics â Rich Experience in:
⣠Using R packages like Slidify and R-Markdown via R-Studio
⣠Visualization libraries like Plotly, ggplot2, googleVis etc.
⣠Creating Tableau Applications / Dashboards
o Machine Learning and Predictive Analytics â Extremely Adept in:
Supervised Learning:
Classification
⣠Logistic Regression
⣠Decision/Classification Trees (CART)
⣠Support Vector Machine
⣠Ensemble techniques â Random Forest (Bagging), Gradient Boosting â GBM, XGBoost etc.
⣠Model Verification and Validation â AUC/ROC, Misclassification Error, Confusion Matrix, Sensitivity/Specificity, TPR/FPR, Gini Index etc.
Regression
⣠Linear Regression
⣠Linear/Quadratic Discriminant Analysis
⣠Regression Trees (CART)
⣠Model Verification and Validation â Root Mean Squared Error, R-Squared, T-Stat, F-Stat, P-Stat (Variable Significance)
Unsupervised Learning:
Clustering
⣠K-Means
⣠Hierarchical
⣠Mean-Shift
Association Rule Mining
⣠Apriori Algorithm
o Statistics Basics - Adept in Probability Theorem, Hypothesis Testing, Standard Normal, Central Limit Theorem, Z-Test, T-Test, ANOVA / F-Test, Chi-Square Test, Poisson Distribution, Binomial Distribution etc.
o Data Science Trainer and Mentor (Online and Classroom) â Have experience in Training and Mentoring Students who have enrolled for extensive online Data Science Courses. E.g. Springboard. Have also tutored students in Classroom Trainings.
o Data Quality Management â Part of Creation, Review and Updation of Data Transmission Policies with the Contract Manufacturers (Cisco). Created an End-to-End solution to:
⣠Test data health across the downstream systems
⣠Publish the results (tableau reports and mailers)
⣠Alert in case of issues (Workflow)
⣠Measure & report partner level KPIs in form of metrics/scores
⣠Drive the closure of issues with the partners
o Process Quality Management â Spearheaded Defect Prevention activities like â
⣠Application of Kaizen principles
⣠Defect Classification
⣠Ishikawa (Fish Bone) Analysis
⣠Pareto Principles
Have assisted teams in identifying the major issues causing most of the defects in their functions.
o System Analysis â Analyzed complex and heterogeneous landscapes of backend systems to improve system resilience. This involved:
⣠Identification of critical system path(s) and the bottlenecks on those critical paths
⣠Coming up with hotspots / vulnerable applications
⣠Updating the risk register
⣠Devising mitigation plans and disaster recovery plans
⣠Proposing remediation projects
o Project and Program Management - Have Managed End-to-End Project Implementations.
⣠Experience in Agile and Waterfall Methodologies of Project and Program Management.
⣠Obtained PMP certification.
o SAP - Extensive Knowledge in SAP â Supplier Relationship Management, Finance, Material and Inventory Management etc.
Data Science Certifications:
Institute: Indian Institute of Management, Bangalore
Mode: Classroom
Year: 2016 â 2017
Johns Hopkins University School of Education
Mode: Online
Year: 2015 â 2016
Tutoring Approach
I believe in providing a Comprehensive tutoring which would bring value and make the students more confident in the subject. Even though it may take more time and effort, but I believe that each moment invested by the students and myself should be worthy and beneficial.