Yi Wang is an Application Engineering Manager at MathWorks based in Natick, MA USA.
He specializes in financial modeling, application deployment, and parallel computing with MATLAB.
Before joining MathWorks in 2007, he worked at Motorola in Illinois for seven years as a software engineer in wireless communications product development.
In his current role, Yi has worked with MATLAB users in Finance, Energy, CES, and other industries, helping them adopt MATLAB to build robust and powerful models efficiently and take their models to integrate with other systems in the Cloud. Yi has conducted MATLAB seminars and workshops at various banks/hedge funds, engineering firms, and universities.
Yi holds a Bachelor of Applied Science in Computer Engineering from the University of Toronto and an M.S. in Computer Science from the University of Southern California.
Application Engineering Manager MathWorks
Topic 1: AI, Machine Learning and Deep Learning for Finance with MATLAB
Big data and AI represent an opportunity to impact the bottom line of financial institutions. By building advanced analytics and machine learning models on top of these large repositories of data, business decisions can be vastly improved. Some tasks that stand to gain the most from such improvements include: process automation, stock selection models, risk modeling, fraud detection, determining trading opportunities, underwriting, improving the customer experience/journey, and even forecasting which employees are at risk for switching companies.
In this session, we will introduce how to build AI models through various econometric, machine learning, and deep learning examples in MATLAB. We will also talk about presenting these insights and models to business users and customers in the form of easy to use interfaces and through automated report generation.
And finally, we’ll try to touch on something that is as important as the modeling - How do we take these models through the model validation, model review and regulatory process?
Using Neural networks, deep learning, supervised and unsupervised machine learning techniques to enhance traditional Financial modeling approaches
Building Deep Learning LSTM models for sequence/time series data; Using TensorFlow and MATLAB
Identifying Alpha or Risks stemming from unstructured data like News or Twitter using NLP, specifically Sentiment Analysis and Topic Modeling
Automated predictor selection, cross validation, and hyperparameter tuning
Leveraging auto-documentation of complex modeling for reporting purposes
Using MATLAB’s Model Risk environment to sell Machine Learning (and other traditional) models to review committees, validation teams and regulators
Scaling and increasing performance with multiple processors, clusters, and the Cloud
Data management and integration with Databases, Datafeeds like Bloomberg, Excel, HDFS/Hadoop, and Big Data environments and GPU code generation
Powerful tools to take prototypes into production: Deploying to Python, Excel, the Web
Topic 2 : Scaling Data Analytics to Cloud using MATLAB
This presentation and demo highlight the use of MATLAB as a data analytics platform with best-in-class stream processing frameworks and cloud infrastructure to express MATLAB based workflows that enable decision-making in “near-real-time” through the application of machine learning models. This includes model development and validation on large historical data sets and additional considerations for implementing the model on new, incoming data. The architectural design for a cloud-based platform that operationalizes these advanced analytics using a typical lambda architecture consisting of both the batch processing methods and stream processing is discussed in detail. This talk will also highlight the value of exposing the functionality through API layers, designed to make these systems more secure and extensible and better enable decision-making.
The demonstration shows a full workflow from the development of a machine learning model in MATLAB to deploying it to work with a real-world sized problem running on the cloud.
Data preprocessing, analysis, and modeling are performed at-scale in the batch layer on a distributed storage system and leverages Apache Spark.
Model development and validation on large amounts of simulated data is discussed.
It demonstrates how to use MATLAB Production Server™ to deploy these models on streams of data from Apache® Kafka®.