Senior Data Scientist Resume

SUMMARY:

Data scientist with extensive industry experience with big data, and advanced skills in statistics and machine learning
10+ years of experience of programming and software development
Author of a publicly available R package (30000+ downloads to date)
Significant research experience as demonstrated by awards, publications and presentations

PROFESSIONAL EXPERIENCE:

Senior Data Scientist

Confidential

Spearheaded the effort to extend the capability of in - house A/B testing infrastructure to measure the impact of advertising on AppStore, and published reports post-launch
Defined success metrics for AppStore and Confidential Music search in live experiments
Led studies to relate user engagement and conversion with site speed performance, successfully living up to the challenge of connecting separate data sources for prompt delivery
Produced A/B test readouts to drive launch decisions for search algorithms including query refinement, topic modeling, signal boosting and machine-learned weights for ranking signals
Built automated pipelines to generate and incrementally update evaluation sets with metadata enrichment for human judgment of search quality
Designed tailored sampling methodology to build evaluation sets for different features
Designed and executed an evaluation plan to compare the search relevance of AppStore with competitors Technologies: R, SQL, Hadoop, Spark, Hive, Scala, Python, Splunk, Postgres, GitHub, Shell script

Staff Data Scientist

Confidential

Developed clustering methodology to personalize timing for sending push notifications, delivering significant engagement improvement (50%+ lift in click-through rate; 10% lift in mobile traffic)
Spot Award for pioneering experimentation of the notification service on the mobile platform, and for delivering significant improvement in user engagement
Developed an automated pipeline to monitor the quality of Confidential category recommendation engine by computing sellers’ acceptance rates in creating listings
Devised an auto-labeling strategy to create training data for classifying listings to product type, achieving the target precision goals (90%)
Deployed scalable, in-house machine-learning solutions in distributed systems to address high-value business questions
Improved lift estimation in A/B testing by means of mixture modeling coupled with bootstrapping
Sped up report generation by 80% on the experimentation platform, implementing in-database computation in R
Built a web app in R embedded with Teradata access to retrieve the activity log of any Confidential user

Technologies: R, SQL, Teradata, Hadoop, Hive, Scala, Scalding, Python, parallel computing, in-database analytics, JDBC/ODBC, BTEQ, GitHub, Shell script, C, SAS, Matlab, MicroStrategy

Postdoctoral Senior Fellow

Confidential

Developed supervised methodology based on Bayesian model averaging of regression models to construct gene regulatory networks from high-dimensional genetic data
Collaborated with a cross-disciplinary team of research scientists and offered them statistical consultation Publications:
K Lo, A Raftery, K Dombek, et al. (2012). Integrating external biological knowledge in the construction of regulatory networks from time-series expression data. BMC Systems Biology.
KY Yeung, K Dombek, K Lo, et al. (2011). Construction of regulatory networks using expression time-series data of a genotyped population. Proceedings of the National Academy of Sciences of the USA.

Technologies: R, parallel computing, C, GNU Scientific Library, Perl, Matlab, LaTeX

Intern

Confidential

Developed an automated pipeline to identify discriminating features and to construct classifiers for cancer patients
Developed on-site computing facilities and configured the computing systems for the research team Publications:
A Bashashati, K Lo, R Gottardo, et al. (2009). A pipeline for automated analysis of flow cytometry data: preliminary results on lymphoma sub-type diagnosis. IEEE Engineering in Medicine and Biology Society.
K Lo, R Brinkman, R Gottardo (2008). Automated gating of flow cytometry data via robust model-based clustering. Cytometry Part A. (cited 100+ times)

We provide IT Staff Augmentation Services!

We'd love your feedback!

Resume Categories

Client Services

Job Seekers

Visa Sponsorship