Evan Koh, PhD

My name is Evan Koh and I hold a Ph.D. in Computer Science (Bioinformatics).

I have more than 15 years of experience in data mining and software engineering across a variety of fields - biological, financial, social gaming, e-commerce and web data.

Combining my passion for investing and knowledge in software engineering, I have built a web portal that help investors manage their portfolio intelligently.

I enjoy challenges and working on projects that can impact lives.

Outside of work, I love sports and also enjoy pushing my limits in this area.

I have completed an Ironman (see story), several marathons, was on the university’s dragon boat team and have been snowboarding and skiing since coming to Japan. I never say no to sports.

Personal Achievements

Undergraduate Graduation Representative, Excellence in Research & Sports

National University of Singapore Jul 2008

Chosen among 8,733 to meet the President of Singapore and interviewed by a National Newspaper

See certificate

Ironman Langkawi

Ironman Feb 2007

Completed the extreme triathlon comprising of a 3.8km swim, 180.2km cycle, 42.2km run

2009 World Games Kaohsiung Pre-event

World Games Oct 2006

Represented Singapore in the Dragon Boat World Championship Pre-event held in Taiwan

Fun facts

Random facts about me

Education

Visiting Graduate Student

Laboratory of DNA Information Analysis, Human Genome Center, Institue of Medical Science, University of Tokyo

Jun 2009 – Mar 2011 Tokyo

Doctor of Philosophy in Computational Biology

National University of Singapore Graduate School for Integrative Sciences and Engineering

Aug 2008 – Sep 2012 Singapore

Thesis submitted 22 September 2012

Bachelor of Computing in Computational Biology

National University of Singapore

Aug 2004 – May 2008 Singapore

Graduated with Second Class (Upper Division) Honors

Diploma in Multimedia & Infocomm Technology With Merit

Nanyang Polytechnic Singapore

Jul 1999 – Jun 2002 Singapore

Graduated second in cohort

Awards

Granted Scholarship for PhD study (approx. SGD 250,000)

National University of Singapore Graduate School for Integrative Sciences and Engineering Aug 2008

Top 2 students in the Undergraduate Research Opportunity Program

Defence Science & Technology Agency Prize Jun 2008

Top 2nd person in graduating cohort

IBM Singapore Silver Medal Aug 2002

Most outstanding Final Year Project in graduating cohort

IBM Singapore Book Prize Aug 2002

Experience

Work experience (Full-time)

Software Engineer → Senior Software Engineer → Senior Data Scientist → Data Science Manager

Indeed, Inc.

Aug 2014 – Present Tokyo

Built full-stack architecture & data science solutions for Recommendation, Spam Detection, and Jobs Discovery, among others
Design interview questions and perform both Software Engineering and Data Science interviews with >500 hours of interviewing

Data Scientist

Rakuten, Inc.

Aug 2013 – Jul 2014 Tokyo

Optimized Rakuten Ichiba’s Ad platform (such as keyword extraction, paid search ranking logic, optimal ad pricing)
Proposed and executed customer acquisition and nurturing strategies/algorithms for Kobo business

Web Engineer

DeNA Co. Ltd.

Oct 2012 – Jul 2013 Tokyo

Web engineer in an IT company with the main revenue coming from mobile games
Involved in the Mixi-Mobage project and devised the game popularity ranking algorithm

Experience

Work experience (Part-time) and Internship

Research Analyst

Four Elements Capital Ltd.

Mar 2012 – May 2012 Singapore

Research Analyst in a Systematic Commodity Hedge Fund
Responsible for the collection, data analysis and indicators of the grains industry

Software Engineer

HedgeSPA Pte. Ltd.

Dec 2011 – Feb 2012 Singapore

Software Engineer in a Risk Analysis Software Development Firm
Back-end performance tuning. Improved runtime of numerous functions by >50%

Scientific Programmer

Google Summer of Code 2011

Apr 2011 – Aug 2011

Scientific Programmer for an open source project, BioJava
Eventually lead to a scientific publication

Teaching Assistant

National University of Singapore

Aug 2008 – Dec 2008 Singapore

Teaching Assistant for “Introduction to Computing” module to non-computing students
General consensus of end-semester students’ feedback: A friendly and approachable tutor

Research Assistant

Kent Ridge Digital Labs (Currently known as I2R)

Oct 2001 – Nov 2001 Singapore

Research Assistant in the bioinformatics lab of a Research Institute
Led to my first publication before I started my undergraduate studies

Publications

Chuan Hock Koh and Limsoon Wong (2012). Embracing noise to improve cross batch prediction accuracy. BMC Systems Biology.

PDF DOI

Chuan Hock Koh, Sucheendra K. Palaniappan, P. S. Thiagarajan and Limsoon Wong (2012). Improved statistical model checking methods for pathway analysis. BMC Bioinformatics.

PDF DOI

Julian Lai, Chuan Hock Koh, Monika Tjota, Laurent Pieuchot, Vignesh Raman, Karthik Balakrishna Chandrababu, Daiwen Yang, Limsoon Wong and Gregory Jedd (2012). Intrinsically disordered proteins aggregate at fungal cell to cell channels and regulate multicellular homeostasis. PNAS.

PDF DOI

Andreas Prlic, Andrew Yates, Spencer E. Bliven, Peter W. Rose, Julius Jacobsen, Peter V. Troshin, Mark Chapman, Jianjiong Gao, Chuan Hock Koh, et al. (2012). BioJava: an open source framework for bioinformatics in 2012. Bioinformatics.

PDF DOI

Alok Sharma, Chuan Hock Koh, Seiya Imoto, Satoru Miyano (2011). Strategy of finding the optimal number of features on gene expression data. Electronics Letters.

PDF DOI

Chen Li, Masao Nagasaki, Chuan Hock Koh, Satoru Miyano (2011). Online model checking approach based parameter estimation to a neuronal fate decision simulation model in C. elegans with HFPNe. Molecular Biosystems.

PDF DOI

Chuan Hock Koh, Masao Nagasaki, Ayumu Saito, Chen Li, Limsoon Wong, Satoru Miyano (2011). MIRACH: efficient model checker for quantitative biological pathway models. Bioinformatics.

PDF DOI

Chuan Hock Koh, Masao Nagasaki, Ayumu Saito, Limsoon Wong, Satoru Miyano (2010). DA 1.0: Parameter estimation of biological pathways using data assimilation approach. Bioinformatics.

PDF DOI

Chuan Hock Koh, Sharene Lin, Gregory Jedd, Limsoon Wong (2009). Sirius PSB: a generic system for analysis of biological sequences. Journal of Bioinformatics and Computational Biology.

PDF DOI

Chuan Hock Koh, Limsoon Wong (2007). Recognition of polyadenylation sites from arabidopsis genomic sequences. Genome Informatics.

PDF DOI

Vladimir B. Bajic, Vidhu Choudhary, Chuan Hock Koh (2004). Content analysis of the core promoter region of human genes. In Silico Biology.

PDF

Projects

Websites and software I have built

Have you always wanted to invest your money but overwhelmed by the amount of data out and never got started? StocksCafe aims to provide you with actionable information in an easy to digest approach so that you can start investing today!

BioJava - Java Framework for Processing Biological Data

BioJava is an open-source project dedicated to providing a Java framework for processing biological data. It provides analytical and statistical routines, parsers for common file formats and allows the manipulation of sequences and 3D structures. The goal of the Biojava project is to facilitate rapid application development of bioinformatics and I was a significant contributor of this project.

Mirach - Biological Pathway Model Checker

A Statistical Online Model Checker for Biological Pathway Models, based on the PLTLs formalism for expressing the rules/properties to be checked. MIRACH can currently check pathways models written in popular formats such as CSML or SBML.

Data Assimilation - Parameter Estimation in Biochemical Pathway

Data Assimilation (DA) is a computational approach that estimates unknown parameters in a pathway model using time-course data. Here, we developed a Java software with an intuitive interface to allow users to carry out parameters estimation using DA.

Slides Follow

Sirius PSB - Biological Sequence Analysis

Sirius Prediction System Builder (Sirius PSB) is a software package designed to enable biologists with little or no computing knowledge to carry out sequence analysis using computational methods with ease and speed via a graphical user interface. Built into the software is the ability to build high-quality prediction models, visualization, multi-dimensional protein search, and more.