Quantcon 2015 – Live Streaming Conference

QuantCon 2015, a disruptive quant trading event, will break down the existing walls to algorithmic trading by giving you an inside look at tools and content sets typically available only to Wall Street.

 
Through key experts leading innovative talks and workshops, you will learn how to improve your investment performance by exploring algorithmic trading strategies and applying open-sourced ethos to your investment ideas.

Attend and come away feeling empowered and prepared to advance your investment strategies.

Event Date and Time : March 14 2015 (8.15 am -6 00 pm EDT)

What you will get?

We need 100 viewers to make the live streaming successful – a critical mass to make the online experience exciting and engaging.

You’ll get access to the live stream and a dedicated chat room.

Workshops & Talks

Wall Street: A Comparative Study of Trading Strategies Sourced from ‘Pros’ Versus ‘the Crowd’ by Lisa Borland, Head of Research and Co-Portfolio Manager at T2AM

Beware of Low Frequency Data, Ernest Chan, Managing Member, QTS Capital Management, LLC.

It is commonly believed that low frequency strategies require only low frequency data for backtesting. We will show that using low frequency data can lead to dangerously inflated backtest results even for low frequency strategies. Examples will be drawn from a closed end fund strategy, a long-short stock strategy, and a futures strategy.

Market Outlook 2015: How to Spot Bubbles, Avoid Market Crashes and Earn Big Returns, Mebane Faber, Co-founder and Chief Investment Officer of Cambria Investment Management
Attend Mebane’s Meeting and Learn…
– Why a traditional 60/40 allocation will not get you to 8%
– How to value international stock markets
– How to avoid market bubbles and buy when “blood is in the streets”
– How to create a trading system to always invest in the cheapest markets

Investment bubbles and speculative manias have likely existed for as long as humans have been involved in markets. How can investors identify and avoid these bubbles’ bursts and losses, and even profit from these crashes? Building on Graham and Dodd’s work, Robert Schiller popularized CAPE, his version of the cyclically adjusted price-to-earnings ratio, in the late 1990s to give timely warnings of poor stock returns. Mebane Faber applies this valuation metric across more than 30 foreign markets and finds it both practical and useful. This presentation will describe a trading system to build global stock portfolios based on valuation, which can lead to significant outperformance by selecting markets based on relative and absolute valuation.

How Women are Conquering the S&P 500 by Karen Rubin, Director of Product at Quantopian

According to Credit Suisse’s Gender 3000 report, at the end of 2013, women accounted for 12.9% of top management in 3000 companies across 40 countries. Since 2009, companies with women as 25-50% of their management team returned 22-29%. If companies with women in management outperform, what would happen if you invested in women-led companies? Karen Rubin will explore this question in the Quantopian research platform and share her findings.

Case Studies in Creating Quant Models from Large Scale Unstructured Text, Sameena Shah, Director of Research, Thomson Reuters 

SEC filings provide a window into the health of the company and are immensely important for investors. Historically, the only feasible way to read and interpret filings has been manually, where domain experts interpret filings and provide guidance to public. However, advances in big data technologies and Natural Language processing have enabled its automation. Sameena will discuss how her team created predictive models from text in filings and social media.

10 Ways Backtests Lie, Tucker Balch, Co-founder and CTO of Lucena Research

“I’ve never seen a bad backtest” — Dimitris Melas, head of research at MSCI. Quantitative Analysts rely heavily on backtests as a means of validating their trading strategies. All too often, strategies look great in simulation but fail to live up to their promise in live trading. There are a number of reasons for these failures, some of which are beyond the control of a quant developer. But other failures are caused by common but insidious mistakes. In this talk I’ll review a list of 10 pitfalls in strategy development and testing that can result in optimistic backtests. I’ll also present methods for detecting and avoiding them. This talk will be of interest to quant developers and also non-quants who are interested to know what to look out for when presented with remarkably successful backtests.

Staying Ahead of the Game, Sarah Biller, Chief Operating Officer for Innovation at State Street Global Exchange

Across the past decade, trading volumes have grown exponentially. Technology has advanced at light speed. Sources of investable information have exploded. Enabled to invest faster with data and insights from alternative sources that lead many to question the relevance of fundamental data, equity investors today differ from those of the past. With this massive, permanent change to the investment environment comes opportunity. Sarah will discuss new sources of data and investment analytics that help quant investors make sense of the change.

The Machine Learning Approach, Michael Kearns, Professor of Computer and Information Science, UPenn
Traditional financial markets have undergone rapid technological change due to increased automation and the introduction of new exchanges and mechanisms. Such changes have brought with them challenging new problems in algorithmic trading, many of which invite a machine learning approach. In this talk, Michael will examine several algorithmic trading problems, focusing on their novel ML aspects, including limiting market impact, dealing with censored data, and incorporating risk considerations.

The Genesis of An Order Type, Dan Aisen,  Co-founder and Quantitative Developer at IEX

For the past several years, exchange and dark pool order types have been one of the hot topics in the US equity markets, as characterized by WSJ exposes and record SEC fines. Rather than piling on with more negativity, this talk will walk through the process of developing a new order type, from the discovery of a market structure inefficiency to the research of potential solutions, and finally, the deployment and evaluation of the result. This talk will explore how exchanges and dark pools can impact the stock market through thoughtful order type design.

The Mobile Revolution and the Future of Modern Data Collection, Joe Reisinger, Co-founder and CTO of Premise

Orchestrating the collection and refinement of large-scale geospatial, economic and human development data — data which form critical inputs for businesses, investors, policy-makers, regulators and strategists looking to get a timely and accurate read for what’s happening right now on the ground — is slow, difficult, and expensive. In many countries, such data pipelines don’t exist yet at all. The proliferation of internet-enabled smartphones, with users spanning from globe from Mississippi to Mozambique, is rapidly changing our capabilities in this sector — and Premise is upending the model by blending modern technology with human intelligence to map reality on the ground faster and more precisely than ever before. In this talk, Premise CTO Joe Reisinger will talk about the evolution of modern data collection on a global scale, why the new frontier of mobile technology is the conduit for the future of business and economics, and the role of alternative economic data as it relates to collection of official government statistics.

Moving Data Science from Pain to “Unicorns on Rainbows”, Brian Granger, a Leader of the IPython project, co-founder of Project Jupyter

Data scientists experience various pain points when working with code and data. The current generation of software tools inhibits collaboration, confuses users, burdens users with high cognitive loads, exhibits poor visual and interaction design, is overly proprietary and expensive, prevents reproducibility and limits the creation of coherent data-driven narratives. Project Jupyter, (formerly IPython) a set of open-source software projects for interactive and exploratory computing, is attempting to address the above pain points. This talk will focus on user interfaces and visualizations, the collaboration and sharing of computational narratives and the deployment of our software within companies, research groups and the open internet. The reduction of pain will be illustrated by giving numerous examples of how different organizations are leveraging the Jupyter Notebook. However, I will be honest about the vast amount of work we have left to do before delivering on our promise of “Unicorns on Rainbows.”

Probabilistic Programming in Quantitative Finance, Thomas Wiecki, Lead Data Scientist at Quantopian

There exist a large number of metrics to evaluate the performance-risk trade-off of a portfolio. Although those metrics have proven to be useful tools in practice, most of them require a large amount of data and implicitly assume returns to be normally distributed. Bayesian modeling is a statistical framework that allows great flexibility in modeling financial returns as well as risk metrics. In addition, uncertainty of these metrics can be directly quantified in terms of the posterior distribution.
In this talk, Thomas will briefly provide an overview of Bayesian statistics and how Probabilistic Programming frameworks like PyMC can be used to build and estimate complex statistical models. He will then show how several common financial risk metrics like the Sharpe ratio can be expressed as a probabilistic program. Using real-world data from anonymized algorithms running on Quantopian, he will demonstrate how the normality assumption can strongly bias the Sharpe ratio and how heavy-tailed distributions can remedy this problem.

Leveraging Quandl, Tammer Kamel, co-founder and CEO of Quandl.com 

This will be a demonstration-based working session on how to leverage financial data via Quandl from various tools including Quantopian, R and Python. The talk will cover basic and advanced data access methods and also present an overview of the free and commercial data available on Quandl.com.

Turkey or Trader? Jeremiah Lowen, Director of Risk Management at Kokino LLC

Backtests can be treacherous. Though most quants quickly acknowledge that “past performance is not indicative of future returns,” many still evaluate algorithms solely through backtests. In this talk, we will discuss common pitfalls of interpreting and extrapolating hypothetical results. We adopt a skeptic’s view of quantitative investing and examine the various biases and errors that quants can introduce even as they follow “best practices.” Ultimately, we will try to understand the degree to which we can gain confidence that a backtest is representative of an algorithm’s quality.

Finding Alpha from Stock Buyback Announcements in the Quantopian Research Platform, Anju Marempudi is the founder and CEO of IntelliBusiness and creator of EventVestor and Seong Lee, Client Engineer at Quantopian
Stock buybacks are at record levels and several studies have established windows of alpha opportunity around stock buyback announcements. In this talk EventVestor founder Anju Marempudi and Quantopian client engineer Seong Lee will discuss buyback trends, analyzing share buybacks data for insights, conducting an event study to measure excess returns around buyback announcements, and finally building a trading algorithm with back-testing using the Quantopian Research platform.

Hedge Fund Manager Selection and The Quantopian Open by Justin Lent, Director of Fund Development

From Contest to Hedge Fund: This talk will focus on results of Quantopian’s first monthly trading contest, and how Quantopian will use data and results from its trading contests to inform its hedge fund selection. The discussion will focus on the construction of uncorrelated portfolios, and performance evaluation of strategies based on their backtests and out-of-sample performance.

Democratized Investing, Akhil Lodha, Co-founder of Sliced Investing, and Mesh Lakhani, Founder of FutureInvestor.co

In an ideal world an investor has access to a range of investment opportunities that allow her to create a Balanced portfolio based on her risk/return objectives. Unfortunately we don’t live an in ideal world and a lot of the investment opportunities have only been available to the Institutional Investor. That trend has started to change as technology and innovation by startups like AngelList, Wealthfront, and Sliced Investing, among others are lowering the barrier to access and allowing more individuals to create a balanced portfolio that meets their investment objectives. In this talk we’ll focus on the need for a balanced portfolio, the investing tools for the ‘new-age’ investor and the future of individual investing.

Using Domain Expertise to Improve Text Analysis, Evan Schnidman, Founder and CEO of Prattle Analytics

It is widely acknowledged that text analysis offers a view into a massive world of unstructured data. This data offers a goldmine of tradable information ranging from corporate regulatory filings to central bank communications. But, like other areas of “big data,” this material is virtually useless without narrowing the focus. This talk will examine the ways in which deep domain expertise can help refine text analysis data into a powerful investing tool.