This is a summary of links featured on Quantocracy on Sunday, 02/23/2020. To see our most recent links, visit the Quant Mashup. Read on readers!
-
Model Interpretability: The Model Fingerprint Algorithm [Hudson and Thames]The complexity of machine learning models presents a substantial barrier to their adoption for many investors. The algorithms that generate machine learning predictions are sometimes regarded as a black box and demand interpretation. Yimou Li, David Turkington, and Alireza Yazdani present a framework for demystifying the behavior of machine learning models. They decompose model predictions into
-
All About Time Series: Analysis and Forecasting [Quant Insti]Since predicting the future stock prices in the stock market is crucial for the investors, Time Series and its related concepts help in organizing the data for accurate prediction. In this article, we are focusing on Time Series, its analysis and forecasting. In this article, we aim to cover the following on Time Series: What is Time Series and Time Series Analysis? Types of Time Series What are
-
Rebalancing! Really? [OSM]In our last post, we introduced benchmarking as a way to analyze our heros investment results apart from comparing it to alternate weightings or Sharpe ratios. In this case, the benchmark was meant to capture the returns available to a global aggregate of investable risk assets. If you could own almost every stock and bond globally and in the same proportion as their global contribution, what
-
Detecting market price distortions with neural networks [SR SV]Detecting price deviations from fundamental value is challenging because the fundamental value itself is uncertain. A shortcut for doing so is to look at return time series alone and to detect strict local martingales, i.e. episodes when the risk-neutral return temporarily follows a random walk while medium-term return expectations decline with the forward horizon length. There is a test