Difference between revisions of "CV:General"
Changtau2005 (Talk | contribs) |
Changtau2005 (Talk | contribs) |
||
Line 80: | Line 80: | ||
}} | }} | ||
{{CVContent| | {{CVContent| | ||
− | + | My goal is to model the deterministic component of equities prices and price correlations, via compact feature representations of multiple time series, using layers of convolutional filter banks learned automatically through optimization. I am using Microsoft's CNTK deep learning toolkit and TickData's commercial second-resolution historical dataset for all equities in the S&P500. | |
}} | }} |
Revision as of 22:37, 8 December 2016
Li Quan Khoo | li.khoo.11@ucl.ac.uk | changtau2005@gmail.com |
http://lqkhoo.com/wiki | https://github.com/lqkhoo | |
http://www.linkedin.com/pub/li-quan-khoo/89/a27/8aa |
University College London - MEng Computer Science, First Class Honours | 2011 - 2015
|
- Masters research project - Predicting Personality from Twitter
- Information Retrieval and Data Mining Prize
- Best Research Group Project of the Year - Task Identification using Search Engine Query Logs
- Developed a platform-agnostic home automation system capable of remote surveillance, command and control
- Developed an Android app for the Restless Beings charity to conduct field studies on children in poorly-developed countries
Imperial College London - MBBS Medicine | 2009 - 2011
|
- Withdrew in second year to transition to computer science
Concord College, Shrewsbury - GCE A levels (Pre-A*) - AAAAab | 2008 - 2009
|
- Outstanding Student of the Year 2008 - Double award (Chemistry, Music) | Most imaginative hovercraft design
R&D Scientist - Digital:MR | May 2015 - August 2015
|
4-month feasibility study on sentiment analysis of images in social media, funded by a research grant from the UK technology strategy board. Using the Yfcc100m and YLI datasets comprised of 100 million images, labels, and metadata, I investigated both existing and novel methods to develop a commercially-viable product.
Research Intern - Microsoft Research Cambridge | May 2014 - August 2014
|
8-week research internship through the Bright Minds Intern Competition programme in the Machine Learning and Perception research group, working with Principal / Senior Researchers Pushmeet Kohli, Yoram Bachrach, Ulrich Paquet, and Filip Radlinski.
I worked on Project SmartFence - an application for web access control. Users block or allow the few sites they know and SmartFence infers the suitability for the rest of the web. We developed several different cluster/kernel-based models and visualization schemes, and I delivered a prototype for the OneWeek company-wide hackathon. A patent was applied for.
Founding Developer - Unientry.Ltd | June 2013 - 2014
|
3-month internship to develop a pilot site to help sixth form students find the right university. The platform filters information from the Higher Education Statistics Agency and gives recommendations based on students' registered information and grades.
Site: http://www.unientry.org
JP Morgan Spring Week 2013 - European HQ - 25 Bank St. Canary Wharf | April 2013
|
Implemented an implied volatility calculator for a stream of options prices, using the Black-Scholes model. Team awarded second-best for code review and performance, and best for presentation.
Self-directed research: Deep convnet models for equities pricing | June 2016 - present
|
My goal is to model the deterministic component of equities prices and price correlations, via compact feature representations of multiple time series, using layers of convolutional filter banks learned automatically through optimization. I am using Microsoft's CNTK deep learning toolkit and TickData's commercial second-resolution historical dataset for all equities in the S&P500.
Study trip - Hokkaido Japanese Language School | August 2014 - September 2014
|
Self-funded intensive study trip with home stay in Sapporo, Japan, to supplement my self study.
Academic interests |
Spoken languages and personal interests |