This is a summary of links featured on Quantocracy on Monday, 05/14/2018. To see our most recent links, visit the Quant Mashup. Read on readers!
-
Alpha Momentum [Factor Research]Stocks can be ranked by alpha instead of stock returns Alpha Momentum generates a higher and more consistent performance than Price Momentum Momentum crashes are reduced significantly and risk-return ratios increase INTRODUCTION Alpha in finance is shrinking continuously as investors are getting better at analysing returns. When a fund manager beat his benchmark 30 years ago, investors likely
-
How to Benchmark Trend-Following [Flirting with Models]Benchmarking a trend-following strategy can be a difficult exercise in managing behavioral biases. While the natural tendency is often to benchmark equity trend-following to all-equities (e.g. the S&P 500), this does not accurately give the strategy credit for choosing to be invested when the market is going up. A 50/50 portfolio of equities and cash is generally an appropriate benchmark for
-
Giving Computers the Ability to Learn from Data [Golden Jumper]General concepts of Machine Learning 3 types of learning and basic terminology Supervised learning. Learn a model from labeled training data that allows us to predict future or unknown data. Supervised refers to a set of sample where desired output signals (labels) are already known. Eg spam filter Also known as classification tasks. Another subcategory is regression where the outcome signal
-
SPX Performance Based on SOMA Action During the Present QT Initiative [Quantifiable Edges]The Feds System Open Market Account (SOMA is the account at the Fed that contains all of its bond purchase holdings. Fed SOMA data going back to 2003 can be downloaded from the New York Feds website. Over this time, there has been a strong relationship between the changes in the SOMA and movement in the stock market. I detail this relationship in the recently released Fed-Based Quantifiable