Article

Refining Reconciliation: A Machine Learning Approach to the Financial Industry’s Toughest Task

Posted June 27, 2017 | Leadership | Technology | Amplify
Figure 4b — Rule concision: the worst case.

In this article, we examine different machine learning mechanisms and propose a maximally specific con­junctive approach to fitting massive data sets in the real world of reconciliation. Furthermore, we provide a balanced solution to address the high skewness in reconciliation data sets.

About The Author
Zhuo Li
Zhuo Li is Managing Director in State Street Corporation’s Application Development and Maintenance Department. Dr. Li hasmore than 15 years’ experience in financial technology R&D focusing on transaction processing, data mining, and visualization. He holds a PhD in computer science and an MS degree in management engineering from Zhejiang University. He can be reached at Zhuo_Li@statestreet.com.
Jianling Sun
Jianling Sun is a Professor and Doctoral Supervisor at Zhejiang University, with more than 30 years’ experience in advanced tech­nology R&D. His recent research focuses are data mining, machine learning, and blockchain. He holds a PhD in computer science. He canbe reached at sunjl@zju.edu.cn.
Don’t have a login? Make one! It’s free and gives you access to all Cutter research.