Data Scientist Resume Wilmington, DE - Hire IT People

SUMMARY:

Data scientist with 5.5 years of experience in utilizing machine learning, data processing and data analysis skills to solve challenging analytical problems and aid in business decision making.

SKILLS & TECHNOLOGIES:

Programming: Python, R, SAS, SQL, Java, XML, Shell, Spark, Scala, Pig, Hive, Map Reduce

Software: Anaconda 3.5, Tableau, AWS, SAS Enterprise Miner, R Studio, Postman API

Competencies: Machine Learning, Business Intelligence, Business Analysis, Data Mining, Data Engineering, Statistical Analysis, Time Series Analysis, Forecasting, Anova, A/B Testing, SDLC, Waterfall and Agile

WORK EXPERIENCE:

Confidential

Data Scientist, Wilmington, DE

Responsibilities:

Designing and developing various machine learning algorithms for POC (Proof of Concept) and fraud data pooling
Working on POC’s with Apache Spark APIs over Cloudera Hadoop YARN, used Scala for data processing and performed data analytics on Hive DB
Customizing core libraries to be used by all the team members in the Docker AWS - based analytics environment with other standardized python and R dependencies
Implementing python-based machine learning models as RESTful web services and consuming them using REST APIs
Used random forest algorithm to build a fraud detection model that improved the detection rate of customer fraud by 10%
Used natural language processing toolkit and VADER package for performing sentiment analysis on online customer complaints and identify negative sentiment scores that improved model performance by 15% than traditional model

Confidential

Data Scientist, Overland Park, KS

Responsibilities:

Built a churn prediction model using logistic regression that predicted subscription cancellations and aided business in designing personalized campaigns for the users that reduced churn rate approximately by 4%
Developed various machine learning models for business in the areas of campaign management that demonstrated performances of 80.6% on par with state-of-the-art models used in industry
Used random forest algorithm to help analyze various acquisition campaigns and improve their effectiveness approximately by 80%
Used Spark Streaming APIs to build a common learner data model for near real-time data processing that collects data from Kafka and persists it into Cassandra

Confidential

Data Analyst

Responsibilities:

Built a multi-class classification algorithm that accurately classified credit card holders and improved bank’s efficiency by reducing default rate and offering new product choices to customers
Performed credit scoring analysis to predict whether or not to extend credit limits for a new or an existing applicant and if it results in a profit or loss
Developed various data visualizations using Tableau to analyze data trends over time
Used logistic regression, clustering and multivariate modeling to provide valuable analytical insights
Used Kolmogorov-Smirnov test (K-S test or KS test) to measure the quality of the models, performed feature visualization and used k-fold cross validation to avoid model over fitting

We provide IT Staff Augmentation Services!

Data Scientist Resume

Wilmington, DE

We'd love your feedback!

Resume Categories

Client Services

Job Seekers

Visa Sponsorship