Profile Details

Create Project

★★★★★

☆☆☆☆☆

USD 70 /hr

★★★★★

☆☆☆☆☆

Hire Dr. Ralitza V.

United States

USD 70 /hr

Data Scientist with 10+ years of experience, specializing in predictive modeling and deep learning.

Profile Summary

Data scientist with 10 years industry experience who enjoys developing predictive models and deep learning. Proactively stays up-to-date with latest machine learning techniques. ACCOMPLISHMENTS: Deep Learning: * Develop and train CNN custom loss and WNET architecture for unsupervised semantic segmentation on images. Each image is clustered and areas with similar color are flagged in the same cluster. * Write from scratch and train CNN models for semantic segmentation. Fine tune hyper parameters and adjust performance. * Train CNN models for object localization based on Single Shot MultiBox Detection. * Prototype, build and train LSTM models to classify and forecast sequential data. Models are 98% accurate on test data Predictive Modeling: * Develop and implement models for predicting software regressions using random forests and signal processing to create features. * Predict demographics (age, gender) of the observed non contractual population using techniques like random forests, boosted trees and ensembles. * Develop predictive models (logistic regression, regression trees) to identify matched control groups for marketing campaigns. * Develop predictive models (neural networks, regression trees) for seat upsell opportunities, customer referrers and user behavior. * Develop predictive models for expected customer lifetime (neural networks). Machine Learning: * Develop and implement audience extension algorithm based on locality sensitive hashing. * Design, develop and implement marketing mix optimization model to minimize expense and maximize revenue using mathematical optimization.

Subject Matter Expertise

• ★ Data Science
• ☆ Deep Learning
• ☆ Python

Services

• Research
• Data & AI

Research Systematic Literature Review, Secondary Data Collection

Data & AI Statistical Analysis, Algorithm Design-Non ML

Work Experience

Principal Data Scientist

Decision Sciences

March 2018 - Present

Data Scientist

Teradata

March 2017 - March 2018

Education

Ph.D

University of Massachusetts Amherst

September 1999 - September 2005

Certifications

• Certification details not provided.

Publications

JOURNAL ARTICLE

(2011). An investigation of project complexity's influence on team communication using Monte Carlo simulation. Journal of Engineering and Technology Management, Volume 28, Issue 3, Pages 109–127.

(2010). Team Decision Making in Computer-Supported Cooperative Work: How Initial Computer-Mediated or Face-to-Face Meetings Set the Stage for Later Outcomes. Decision Sciences, vol 41(4), pages 933 - 954.

(2009). The net effect of alternative allocation ratios on recruitment time and trial cost. Clin Trials, vol. 6 no. 2, pages 126-132.

(2004). Exploring why more communication is not better: insights from a computational model of cross-functional teams. Journal of Engineering and Technology Management, Volume 21, Issues 1–2, Pages 83–114.

(2003). Examining a curvilinear relationship between communication frequency and team performance in cross-functional project teams. IEEE Transactions on Engineering Management, 50(3), pp.262-269.