Chen Liu Email & Phone Number

New York, NY, US

New York City Metropolitan Area

Working areas cover Aetna’s medical, dental, vision, voluntary, international, and group retiree insurance businesses and also CVS Health’s PBM business. Collaborated with VP-level stakeholders to define strategic visions to accelerate sales and marketing. Fine-tune the vision and design/implementation analytical plan by conducting focus groups with.

New York City Metropolitan Area

• Established a global Center of Excellence to help Mindshare diffuse AI/ML approach. Collaborated and trained advanced analytics team in Canada, UK, Germany, Singapore, and Mexico. Built a global data service product.
• That assists investment strategy, reveals hidden consumer behavioral patterns, and supports in vestment combination testing and scenario planning across channels, tactics, audience groups, and product categories. 2..
• Used advanced time-series analytics methodologies to predict digital outcomes given digital media budgets. Assessed risk to digital outcomes and power scenario planning across various outcomes (D2C retail, Site.
• Optimize retail digital media spending to achieve given business or media targets.
• Forecasted future performance at daily/weekly level given budgets in various partner sites, such as Amazon, Target, Kroger.4. Market Mix Model5. Customer Digital Attribution Journey
• Used machine-learning algorithm to optimize digital consumer journey at the user level 6. Agent-Based Modeling

Greater New York City Area

Work in marketing intelligence team on data analytics, data transformation and data science.- Developed Market Mix Modeling, Multi-touch Attribution model, forecasting and optimization models for planning/activation team to quantify the advertisement effort. So client can better utilize their marketing dollar, gain full funnel attribution view, and.

Florham Park, NJ

• Director of Data Science under Enterprise Business Intelligent group belonging to Conduent Strategy sector. Lead data sciences across US and Indian to initialize data science capability for various Conduent corporate.
• Data Science Capability - Big data processing using Spark in Azure Databricks - Reporting in Tableau - Data Processing in Alteryx- Advanced Visualization in web based platform utilizing D3 javascript- Data Science.
• IT- Server Storage Optimization and Forcasting- Network Traffic Patter Recognition - Software Utilization
• Finance - Procurement: Asset management - Billing: Account Receivable System Fraud Detection- Profit Decision Support Analysis
• HR:- Employee Attrition/Churning Analysis - Media/Career/Social Media NLP Sentiment Analysis
• Legal:- Government Policy (GDPR) Risk Scanner against Multiple End Point in Database

New York, New York

• Helped Accenture’s clients understand market dynamics using machine learning. Created a simulation framework as a decision-making tool, using multinomial logistic regression, utility theory, Bass diffusion theory.
• Analyzed response of total revenues, loan balance, risk distribution (prime, nonprime, subprime), market share, operational cost, investment payback rate, and vehicle ownership of multiple competitors (Bank, BHPH.
• Investigated impact of car sharing services and autonomous technology on lost ratio and premium price.
• Forecasted U.S. industry wide premium collected will decrease 35% around 60 billion by 2040.
• Recommended a solution of charging new premiums on cyber security, software failure, and infrastructure to mitigate lost. Applying cyber security premium will increase around 15 billion collected premiums. Project 3.
• Broke down insurance premium to liability, comprehensive, and property to detect disruption of car sharing services and autonomous technology on company cost, investment payback rate, vehicle ownership, and crash rate.

Bethpage, New York, United States

• Constructed data profiling, models and applied machine learning by using PySpark, Spark SQL, and MLlib.
• Performed ETL on customer set top box datasets based on specific business rules by using PySpark, Pig, Hive, HDFS, Shell script, SQL and PostgreSQL. PySpark data frame is created on top of Hive table.
• Accomplished performance comparisons of Pyspark and Hive and tuned Pyspark performance in Spark Submit file.
• Partitioned data and automated the data feeding and storage on daily based.
• Followed Agile development method by using JIRA.

- leverage statistical analysis, simulation, machine learning techniques to do marketing research.- segment US automobile market by using technology level data.- forecasted next 15 years autonomous vehicle sales.- built a decision support system to help GM makes technology selection decisions.

Greater Denver Area

• Constructed an on-line platform to analyze data by R, Google Analytics, Excel, WordPress, JavaScript and HTML.
• Built an agent-based simulation to optimize McMurdo Station’s global supply chain network in AnyLogic