Deep Learning

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering

Final Year Thesis Oral Defense

Title: "Deep Learning"

by

DING Hantian

Abstract:

We consider money laundering detection as a machine learning problem. 
Given a list of individual customers with their banking information and 
transaction records, the goal is to find out which of the customers are 
potentially laundering money. Since transactions are essentially 
interactions between customers, we formulate the problem as a graph 
where nodes correspond to customers and edges correspond to transaction 
records. We developed two approaches: recurrent neural network with 
direct embedding and gated graph neural network. Both methods aim to 
embed nodes into low dimensional vectors which can then be used for 
classification.


Date            : 25 April 2018 (Wednesday)

Time            : 18:00 - 19:00

Venue           : Room 2304 (via lifts 17/18), HKUST

Advisor         : Prof. KWOK James Tin-Yau

2nd Reader      : Prof. CHAN Shueng-Han Gary