Isaac Lee
Summary • 424-***-**** • adbx66@r.postjobfree.com • linkedin.com/in/isaaclee6361 • github.com/isaacl312
*
Junior data scientist with 2+ years. Passionate about derive practical solutions and product growth. Improved 37% in client satisfaction ratings and 28% in sales growth. Skilled in ML, statistics, BI, distributed data processing, growth analytics, and collaborative problems solving
Tech Skills
Technical: strong SQL, python(pandas, statsmodel, spark, tensorflow, sklean, matplotlib, django, dash), R, javascript Tools: ELK, spark, hive, redshift, graphql, zeppelin, tableau, dash, tensorboard, google analytics, optimizely Analytics: regression, classification, clustering, time series, NLP, NN, EDA, experiments design, hypothesis, A/B testing Interest: psychology(cognitive, analysis), physics, philosophy, behavior economics, marketing, big data frameworks Experience
EIG, LLC Santa Monica
Data Scientist – Growth (Investment Advisor – Portfolio Manager) 9. 2017 – 8. 2018
Defined OMTM for each teams through performing revenue/cost assessments, built KPI dashboards which decompo se metrics by causal effects, and communicated analyses to stakeholders to devise growth opportunity
Partnered with sales teams, developed a smart CRM planner, schedulers with personalized client review guides int egrated with analytics(segmentation, CLTV, churn, next purchase), resulting in improved sales growth rate by 28%
Designed, implemented A/B testing for marketing campaigns and personalized reports model with Optimizely, and assisted the VP of marketing to devise next version, resulting in improved client satisfaction ratings by 37% yoy SEIA, LLC Los Angeles
Business Analyst – Growth (Investment Advisor - Intern) 11. 2016 – 1. 2017
Performed BCG market assessments on (key market, competitive, customer trends/values, company capability) and customer analytics on (segmentations with preferences and KBF, funnels/cohorts analysis with engagements) o Devised predictive KPI to provide real-time performances and strategic insights for sales teams o Built predictive models (CLTV, churn, next purchase) with dashboards to target marketing for retention efforts o Communicated analyses to cross functional stakeholders, explained casualty and areas for improvements
Assisted a lead data scientist, designed controlled experiments to test data-backed hypotheses, built dashboards to track progresses of feature rollouts and impacts of campaigns, and provided in depth analyses to stakeholders ITPM, LP Remote London
Data Scientist – Inference (Quant fund - Intern) 1. 2016 – 6. 2016
Refined predictive models for value chain metrics with utilizing spatial and NLP, which reduced model error by 11%, provided enhanced forecast to managers, which contributed to improve sharp ratio by 35% yoy
Built a portfolio optimizing tool which statistically computes optimal size, stop loss/ soft target in a given market, and provided quantified risks to managers which contributed to improve mean of Kelly ratio by 13% yoy Attis Capital, LP New York
Data Scientist – Operation (Quant fund - Intern) 6. 2015 – 9. 2015
Performed EDA on large time series data with spark, decomposed causality networks of future markets with eight different methods, and built regularized probabilistic tic arbitrages models with exponential regressions and QDA
Built a real-time risk monitor which decomposes P/L and detects anomalies, resulting in reduced VAR by 9% qoq Education
B.A Economics & Statistics (class of 2017) - (UCLA) Coursework: econometrics, marketing (B2B, B2C), probability, bayesian, data structure/algorithm, distributed system, ML Data Science Bootcamp (2019-2020) - (Laioffer)
Coursework: product growth (market sensing, EDA, hypothesis generating framework) causal inference (experiments design, A/B testing(methods, bays, MAB), non-experimental methods) Projects (GitHub)
Product Analytics – (non contractual: e-commerce, m-games) (contractual: SaaS)
Compute with SQL (metrics, audiences, retentions, cohorts, funnels )
Modeling with Py (segmentations, predict (LTV, churn, next purchase day, metrics)
Causal Inference (experiments design, A/B testing, causality(measure effects, investigate KPI) Kaggle – (regressor, classifier, time series forecasting, anomaly detention)
CTR prediction, credit default, insurance claim, topic modeling, order fraud, KPI anomaly, ETA, metrics forecasting