Uncertainty quantified as probability is the rock upon which Bayesian inference is built. The instability of sample covariance matrices leads to major problems in Markowitz portfolio optimization. In this talk, we use probabilistic programming to compute probability distributions on the covariance of a set of assets. This yields a more robust estimate of their variation and adds uncertainty into how we calculate weights for a portfolio of assets.
In this talk we discuss how to build a Twitter sentiment model in Python using Word2Vec and long short-term memory networks (LSTMs), comparing and contrasting with more conventional statistical models. We cover basic Natural Language Processing (NLP) techniques, providing different ways to extract features from text data for use in modeling. We describe a potential use of this sentiment model in developing cross-sectional algorithmic trading signals for factor models, expanding upon previous work using Twitter data.
Finding alpha is a constant search in algorithmic trading. New alpha factors are always exciting, but sometimes you can come up with new trading signals simply by applying novel aggregation techniques to familiar factors. In this talk we will discuss using ensemble learning methods to combine individual weak signals into stronger factors and assessing their predictive power for long-short equity strategies.
Factor modeling is a common topic in quantitative finance. “Smart Beta” ETFs and similar financial products abound, providing a wealth of options to investors. Factor portfolios are constructed by ranking stocks with a combination of fundamental factors and price-based signals. The resulting factors can be used for many purposes, from cross-sectional equity models to risk and performance attribution. In this talk, we discuss what factor modeling is and how to make use of it in a typical quant workflow.
Quantopian Meetup, Santa Clara
In algorithmic trading, information is king. You can tease out an edge to trade on even by using only the most basic properties of time series. In this lecture, we will cover the statistics that ground the trading logic when conducting pairs trades and discuss how to find pairs.