It was another great year for the R/Finance conference, held earlier this month in Chicago. This is normally a fairly private affair: with attendance capped at around 300 people every year, it's a somewhat exclusive gathering of the best and brightest minds from industry and academia in financial data analysis with R. But for the first time this year (and with thanks to sponsorship from Microsoft), videos of the presentations are available for viewing by everyone. I've included the complete list (copied from the R/Finance website) below, but here are a few of my favourites:
- No-Bullshit Data Science. Szilard Pafka's keynote knocks down some of the myths and misconceptions about real-world data science practices.
- Risk Fast and Slow. A rare treat: in his keynote presentation Dave DeMers offers his perspectives on risk, financial engineering, and major financial events from his days the Prediction Company, Black Mesa and other investment houses.
- Syberia: A development framework for R (Robert Krzyzanowski). Syberia is a new operationalization framework for R scripts, applicable for any production workflow using R (not just Finance).
- yuimaGUI: A graphical user interface for the yuima package (Emanuele Guidotti). An impressive front-end to the Yuima project for solving stochastic differential equations.
- Zero-Revelation RegTech: Detecting Risk through Linguistic Analysis of Corporate Emails and News (Seoyoung Kim). A really interesting approach to looking at sentiment (and length!) of emails (here, the Enron corpus) to predict stock prices.
- New Tools for Performing Financial Analysis Within the 'Tidy' Ecosystem (Matt Dancho). This lightning talk shows how you can perform piping (%>%) operations with time series data from zoo and xts.
- The PE package: Modeling private equity in the 21st century (Thomas Harte). An intriguing peek into the mysterious world of private equity finance.
- Project and conquer (Bryan Lewis). A beautifully elegant introduction to the use of projections in Statistics, and a potentially revolutionary application in speeding up calculations with high-dimensional correlations and clusters.
- Detecting Fraud at 1 Million Transactions per Second (David Smith). My own presentation includes a demo of very high-frequency predictions from R models (about which I'll blog more shortly).
You can find an up-to-date version of the table below at the R/Finance website (click on the “Program” tab), and you can also browse the videos at Channel 9. Note that the lightning talk sessions (in orange) are bundled together in a single video, which you can find linked after the first talk in each session.
|Friday, May 19th, 2017|
|09:30 – 09:35||Kickoff (video)|
|09:35 – 09:40||Sponsor Introduction|
|09:40 – 10:10||Marcelo Perlin: GetHFData: An R package for downloading and aggregating high frequency trading data from Bovespa (pdf) (video)|
|Jeffrey Mazar: The obmodeling Package (html)|
|Yuting Tan: Return Volatility, Market Microstructure Noise, and Institutional Investors: Evidence from High Frequency Market (pdf)|
|Stephen Rush: Adverse Selection and Broker Execution (pdf)|
|Jerzy Pawlowski: How Can Machines Learn to Trade? (html)|
|10:10 – 10:30||Michael Hirsch: Revealing High-Frequency Trading Provisions of Liquidity with Visualization in R (html) (video)|
|10:30 – 10:50||Eric Glass: Equity Factor Portfolio Case Study (html) (video)|
|10:50 – 11:10||Break|
|11:10 – 11:30||Seoyoung Kim: Zero-Revelation RegTech: Detecting Risk through Linguistic Analysis of Corporate Emails and News (pdf) (video)|
|11:30 – 12:10||Szilard Pafka: No-Bullshit Data Science (pdf) (video)|
|12:10 – 13:30||Lunch|
|13:30 – 14:00||Francesco Bianchi: Measuring Risk with Continuous Time Generalized Autoregressive Conditional Heteroscedasticity Models (pdf) (video)|
|Eina Ooka: Bunched Random Forest in Monte Carlo Risk Simulation (pdf)|
|Matteo Crimella: Operational Risk Stress Testing: An Empirical Comparison of Machine Learning Algorithms and Time Series Forecasting Methods (pdf)|
|Thomas Zakrzewski: Using R for Regulatory Stress Testing Modeling (pdf)|
|Andy Tang: How much structure is best? (pptx)|
|14:00 – 14:20||Robert McDonald: Ratings and Asset Allocation: An Experimental Analysis (pdf)|
|14:20 – 14:50||Break|
|14:50 – 15:10||Dries Cornilly: Nearest Comoment Estimation with Unobserved Factors and Linear Shrinkage (pdf) (video)|
|15:10 – 15:30||Bernhard Pfaff: R package: mcrp: Multiple criteria risk contribution optimization (pdf) (video)|
|15:30 – 16:00||Oliver Haynold: Practical Options Modeling with the sn Package, Fat Tails, and How to Avoid the Ultraviolet Catastrophe (pdf) (video)|
|Shuang Zhou: A Nonparametric Estimate of the Risk-Neutral Density and Its Applications (pdf)|
|Luis Damiano: A Quick Intro to Hidden Markov Models Applied to Stock Volatility|
|Oleg Bondarenko: Rearrangement Algorithm and Maximum Entropy (pdf)|
|Xin Chen: Risk and Performance Estimator Standard Errors for Serially Correlated Returns (pdf)|
|16:00 – 16:20||Qiang Kou: Text analysis using Apache MxNet (pdf) (video)|
|16:20 – 16:40||Robert Krzyzanowski: Syberia: A development framework for R (pdf) (video)|
|16:40 – 16:52||Matt Dancho: New Tools for Performing Financial Analysis Within the 'Tidy' Ecosystem (pptx) (video)|
|Leonardo Silvestri: ztsdb, a time-series DBMS for R users (pdf)|
|Saturday, May 20th, 2017|
|09:05 – 09:35||Stephen Bronder: Integrating Forecasting and Machine Learning in the mlr Framework (pdf) (video)|
|Leopoldo Catania: Generalized Autoregressive Score Models in R: The GAS Package (pdf)|
|Guanhao Feng: Regularizing Bayesian Predictive Regressions (pdf)|
|Jonas Rende: partialCI: An R package for the analysis of partially cointegrated time series (pdf)|
|Carson Sievert: Interactive visualization for multiple time series (pdf)|
|09:35 – 09:55||Emanuele Guidotti: yuimaGUI: A graphical user interface for the yuima package (pptx) (video)|
|09:55 – 10:15||Daniel Kowal: A Bayesian Multivariate Functional Dynamic Linear Model (pdf) (video)|
|10:15 – 10:45||Break|
|10:45 – 11:05||Jason Foster: Scenario Analysis of Risk Parity using RcppParallel (pdf) (video)|
|11:05 – 11:35||Michael Weylandt: Convex Optimization for High-Dimensional Portfolio Construction (pdf) (video)|
|Lukas Elmiger: Risk Parity Under Parameter Uncertainty (pdf)|
|Ilya Kipnis: Global Adaptive Asset Allocation, and the Possible End of Momentum (pptx)|
|Vyacheslav Arbuzov: Dividend strategy: towards the efficient market (pdf)|
|Nabil Bouamara: The Alpha and Beta of Equity Hedge UCITS Funds – Implications for Momentum Investing (pdf)|
|11:35 – 12:15||Dave DeMers: Risk Fast and Slow (pdf) (video)|
|12:15 – 13:35||Lunch|
|13:35 – 13:55||Matthew Dixon: MLEMVD: A R Package for Maximum Likelihood Estimation of Multivariate Diffusion Models (pdf) (video)|
|13:55 – 14:15||Jonathan Regenstein: Reproducible Finance with R: A Global ETF Map (html) (video)|
|14:15 – 14:35||David Ardia: Markov-Switching GARCH Models in R: The MSGARCH Package (pdf) (video)|
|14:35 – 14:55||Keven Bluteau: Forecasting Performance of Markov-Switching GARCH Models: A Large-Scale Empirical Study (pdf) (video)|
|14:55 – 15:07||Riccardo Porreca: Efficient, Consistent and Flexible Credit Default Simulation (pdf) (video)|
|Maisa Aniceto: Machine Learning and the Analysis of Consumer Lending (pdf)|
|15:07 – 15:27||David Smith: Detecting Fraud at 1 Million Transactions per Second (pptx) (video)|
|15:27 – 15:50||Break|
|15:50 – 16:10||Thomas Harte: The PE package: Modeling private equity in the 21st century (pdf) (video)|
|16:10 – 16:30||Guanhao Feng: The Market for English Premier League (EPL) Odds (pdf) (video)|
|16:30 – 16:50||Bryan Lewis: Project and conquer (html) (video)|