Resume

Sign in

Data Scientist

Location:
Chicago, IL
Salary:
140000
Posted:
November 29, 2020

Contact this candidate

Resume:

Aravind Senthil Kumar

**** * **** *****, *******, IL 60616 • 312-***-**** • adh710@r.postjobfree.com • linkedin.com/in/aravindsenthilkumar EDUCATION

Aug 2019 – May 2021 ILLINOIS INSTITUTE OF TECHNOLOGY Chicago, IL Master of Science in Data Science

Courses: Machine Learning, Deep Learning, Applied Statistics, Big Data, Statistical Learning, Data Mining Jul 2011 – May 2015 SASTRA UNIVERSITY Thanjavur, India Bachelor of Mechanical Engineering

WORK EXPERIENCE

May 2020 – Aug 2020 SERVICENOW, INC. Santa Clara, CA Data Scientist Intern

• Conceptualized and developed 12 new KPIs impacting employee attrition by collaborating with cross-functional teams

• Developed complex SQL queries in SAP HANA for extracting 110+ potential features across multiple tables

• Identified key drivers for employee attrition 6 months prior to actual termination with a sensitivity of 78% by modeling employee attributes through logistic regression, decision trees, random forest and GBM with SMOTE

• Formulated a new key to capture organization hierarchy changes over last 10 years and empowered the HR managers to differentiate between true transfers and a re-organization Feb 2018 – Jul 2019 TIGER ANALYTICS PVT. LTD. Chennai, India Senior Data Analyst, Data Science

• Propelled an end to end propensity modeling framework responsible for 70% reduction in customer acquisition cost

(below $20) through prospecting clients with a high tendency to go through the marketing funnel

• Extracted features using tree-based models - GBM and XGBoost to obtain ~80 potential variables from over 1000 health, credit, and demographic variables based on feature importance; worked with 300M records

• Generated a lift of 1.5x leveraging GLMNet and backward stepwise logistic regression to identify prospective clients for the marketing team during targeted campaigns

Jun 2015 – Feb 2018 LATENTVIEW ANALYTICS PVT. LTD. Chennai, India Senior Data Analyst, Data Science

• Spearheaded a top-performing team of 5 in facilitating requirement analysis, solution design, and framework integration in enhancing return on marketing costs for a leading home services provider

• Modeled Cost-Revenue relationship based on response curves, and maximized total revenue by over $500k with an 18% increase in numbers of placed service orders through non-linear optimization across products, markets, and channels Data Analyst, Data Science

• Created ‘Multivariate Time-Series’ models across Season, Geography, Product Category to determined future demand in terms of number of placed service orders; improved baseline accuracy from 60% to 92% on monthly forecast

• Innovated and automated a solution for collecting data from various web analytics services; achieved an 80% reduction in data collection time and an increase in delivery quality

• Managed tracking KPIs such as Response Time, Trips per Repair, Gap/Surplus at each market segment by preparing well- designed high impact analytical reports, and Tableau dashboards for operations team PROJECTS

FRAUD DETECTION - European cardholders’ dataset from Kaggle Chicago, IL

• Classified a highly imbalanced dataset (fraudulent transactions accounting for 0.17%) with a sensitivity of 72% by leveraging and comparing the performances of Random Forest, Gradient Boosting and CatBoost algorithms IMAGE CLASSIFICATION - HAM10000 image dataset from Kaggle Chicago, IL

• Created an ensemble multi-class classifier using CNN and transfer learning with InceptionV3, ResNet and DenseNet121 architectures in keras to classify 7 types of skin cancer; achieved a test accuracy of 87% with an AUC-ROC score of 0.81 SKILLS

• Quantitative Methods : Supervised Machine Learning (Linear, Logistic, Trees, Random Forest, Boosting, Naïve Bayes, SVM, Neural Net), Unsupervised Machine Learning(Market Basket Analysis, Clustering), Optimization, Dimensionality Reduction, Hypothesis Testing

• Statistics and Modelling : Python (NumPy, Pandas, sklearn, TensorFlow, Keras), R (rpart, dplyr, caret, glmnet)

• Databases : Teradata SQL, MySQL Workbench, Microsoft SQL Server, SAP HANA

• Big Data Platforms : Hadoop, AWS - EMR, S3

• Data Visualization : Tableau, Microsoft Excel – Macros, ggplot2, Matplotlib, seaborn

• Version Control : GitHub and Bitbucket

HONORS

• Acknowledged for expertise in leading a top-performing Market Mix Modeling team with the “Spirit of LatentView” award

• Mentored 100+ recruits and constructed materials for optimizing the effectiveness of company-wide training on R and SQL



Contact this candidate