Hedge Funds’ Use of Alternative, Unstructured Data to Generate Returns

This is a past event

148 people went


Continuing to pull speakers from within our own ranks, we have Gene Ekster shedding light on how hedge funds and other financial firms use data.

About the talk:

In the last 5-10 years, Alternative Data has been quietly transforming the investment process across Wall Street. The buy-side quants aren’t the only ones in on the action, in fact, most stat-arb shops are late to the party. Roughly defined, financial alternative data is the “big data” which doesn't arise from the financial system itself, i.e. not equity stock price / volume data, order book, analyst estimates or info from the SEC filings, etc. It is data from the broader world around us, online transactions, brick and mortar purchases, POS systems, clickstreams and the like. We're going to walk though a few examples of how noisy, unstructured data become an investable signal using tools such as text mining with latent dirichlet allocation. We will show R code for paneling longitudinal data and discuss procedures for reducing bias in these data. However, overall this talk is going to be slightly less technical, with the aim of introducing the audience to the process of how hedge fund portfolio managers and sell-side research analysts are systematically generating returns by leveraging unique primary (bots / scrapers, channel checks) and third party datasets (including data brokers). This includes sourcing, compliance, scrubbing out PII, alpha generation related to revenue estimates and approaches to balance the secret sauce with product transparency. Finally we'll ponder the future of alternative data in finance, aka why just a Bloomberg terminal is no longer enough. If you are interested in becoming more familiar with the topic before the talk, check out http://integrity-research.com/cms/2014/04/big-data-and-investment-research-part-1/ and http://integrity-research.com/cms/2014/04/big-data-and-investment-research-part-2/ .


Gene is a Director of Data Product Development at 1010Data where he and his team use raw alternative data to create research products for the investment industry, often with a consumer retail, housing and technology focus. Previously he has directed and served the R&D teams at SAC Capital / Point72 and ITG / Majestic Research respectively. He has a degree in Artificial Intelligence from U.C. Berkeley and an MBA from Cornell University. In his spare time he enjoys scraping web sites and using an EEG to create art (http://cognichrome.com (http://cognichrome.com/)).

Gene Ekster can be reached via email at geneman at google's email service or via LinkedIn http://www.linkedin.com/pub/gene-ekster-cfa/0/23/622/

Pizza starts at 6:30, giveaways and the talk begin at 7, then after we will go to the bar.