Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hi, I'm Xiaomeng (Shawn) Wan, a Senior Data Scientist with over ten years of experience working with big data technologies and predictive modeling. I specialize in applying machine learning and AI techniques to solve real-world problems in areas like e-commerce, oil and gas, and online publishing. I love transforming complex data into actionable insights that drive business success. Throughout my career, I've worked on a variety of projects from building Spark clusters and training large language models to developing neural networks and optimization models. I'm passionate about using cutting-edge technologies to create impactful solutions and enjoy collaborating with teams to bring data-driven strategies to life.…Hi, I'm Xiaomeng (Shawn) Wan, a Senior Data Scientist with over ten years of experience working with big data technologies and predictive modeling. I specialize in applying machine learning and AI techniques to solve real-world problems in areas like e-commerce, oil and gas, and online publishing. I love transforming complex data into actionable insights that drive business success. Throughout my career, I've worked on a variety of projects from building Spark clusters and training large language models to developing neural networks and optimization models. I'm passionate about using cutting-edge technologies to create impactful solutions and enjoy collaborating with teams to bring data-driven strategies to life.

Xiaomeng (Shawn) Wan

Data Scientist, Developer, AI Engineer, +1





Hi, I'm Xiaomeng (Shawn) Wan, a Senior Data Scientist with over ten years of experience working with big data technologies and predictive modeling. I specialize in applying machine learning and AI techniques to solve real-world problems in areas like e-commerce, oil and gas, and online publishing. I love transforming complex data into actionable insights that drive business success. Throughout my career, I've worked on a variety of projects from building Spark clusters and training large language models to developing neural networks and optimization models. I'm passionate about using cutting-edge technologies to create impactful solutions and enjoy collaborating with teams to bring data-driven strategies to life.…Hi, I'm Xiaomeng (Shawn) Wan, a Senior Data Scientist with over ten years of experience working with big data technologies and predictive modeling. I specialize in applying machine learning and AI techniques to solve real-world problems in areas like e-commerce, oil and gas, and online publishing. I love transforming complex data into actionable insights that drive business success. Throughout my career, I've worked on a variety of projects from building Spark clusters and training large language models to developing neural networks and optimization models. I'm passionate about using cutting-edge technologies to create impactful solutions and enjoy collaborating with teams to bring data-driven strategies to life.

Available to hire

Hi, I’m Xiaomeng (Shawn) Wan, a Senior Data Scientist with over ten years of experience working with big data technologies and predictive modeling. I specialize in applying machine learning and AI techniques to solve real-world problems in areas like e-commerce, oil and gas, and online publishing. I love transforming complex data into actionable insights that drive business success.

Throughout my career, I’ve worked on a variety of projects from building Spark clusters and training large language models to developing neural networks and optimization models. I’m passionate about using cutting-edge technologies to create impactful solutions and enjoy collaborating with teams to bring data-driven strategies to life.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Work Experience

Senior Data Scientist at Fastloop AI

October 31, 2024 - August 1, 2025

Facilitated cloud data migration, performed data analysis, and transformed data into actionable insights using Python and Spark clusters. Built models to predict customer lifetime value, optimize marketing efforts, and personalize advertisements for retailers. Utilized depreciation curves and maintenance data to estimate future equipment costs and optimize maintenance schedules. Trained large language models with Retrieval-Augmented Generation to generate detailed data descriptions from abbreviated schema names. Built agents that translate natural language into SQL queries by prompting LLM model with data schema. Developed an accident reporting dashboard leveraging NLP and LLM-based summarization.

Senior Data Scientist at Ambyint

March 31, 2021 - August 1, 2025

Built a Spark cluster on AWS to process large volumes of unstructured, noisy sensor data, transforming them into structured, clean data for training predictive and optimization models. Developed predictive models for pump jack fillage estimation, equipment failure prediction using Recurrent Neural Networks, and anomaly detection in downhole card images using TensorFlow neural networks. Constructed classification models to identify and categorize production variations based on decline curves.

Co-Founder at Granify

December 31, 2015 - August 1, 2025

Designed and implemented backend systems using Spark and Scala to process large volumes of incoming data and generate real-time dashboards. Developed models to identify potential cart abandoners and designed A/B tests to evaluate model performance. Created models to match and display appropriate campaigns in real time, significantly increasing conversion rates and delivering double-digit revenue growth for clients. Secured $7 million in Series A funding.

Data Scientist at Tynt

December 31, 2011 - August 1, 2025

Built Hadoop clusters to process terabytes of daily data using Hadoop, Pig, and MapReduce. Developed Pig scripts to summarize unstructured data into insightful reports. Identified visitor browsing patterns to help publishers improve online content and engagement. Implemented NLP on visited webpages and copied text to augment visitor profiles and improve ad clickthrough rates. Created in-site search engine and news recommendation system. Developed and patented innovative technology.