OpenNashPodcasts

Person

Peng Cheng

This page collects what Peng Cheng said on the Making Sense podcast from J.P. Morgan, in an episode from its Data Assets & Alpha Group series on demystifying artificial intelligence in finance. Peng Cheng explains how machine learning works and where it is used in investing.

Peng Cheng describes machine learning as a subset of artificial intelligence, in which a model learns its settings from data instead of following fixed rules. Peng Cheng says a support vector machine delivered much better out-of-sample results than several other models when predicting equity futures returns from historical volatility. Peng Cheng also notes that support vector regression is computationally heavy and does not scale well to large problems.

1 episodes · 10 quoted claims

Peng Cheng says that, unlike a rule-based strategy, a machine learning model learns its parameters from data and finds their optimal values itself.

“But machine learning will actually learn these parameters by itself based on the data and find out what their optimal values are.”

Making Sense (J.P. Morgan) · 0:02:10

Peng Cheng says statistics has historically valued parsimony, meaning as few parameters as possible, partly because computing power was limited.

“historically, statistics have always valued parsimony, which means to have as few parameters, as few coefficients as possible in the model”

Making Sense (J.P. Morgan) · 0:06:42

Peng Cheng says that 30 explanatory variables on 1,000 observations is not enough to cause overfitting.

“it's totally okay if we have a thousand observations and 30 explanatory variables.”

Making Sense (J.P. Morgan) · 0:07:58

Peng Cheng gives stock tracking as a use for lasso: a portfolio may be limited to about 30 stocks, so the number of variables must be restricted.

“if I want to track a stock with a portfolio of stocks, sometimes I cannot have 500 stocks tracking this one stock.”

Making Sense (J.P. Morgan) · 0:10:44

Peng Cheng says decision trees capture discrete nonlinear relationships well but handle continuous ones poorly.

“if you think about trees, they are pretty good at capturing nonlinear relationships, but only the discrete ones, right?”

Making Sense (J.P. Morgan) · 0:19:45

Peng Cheng says support vector regression was developed in the 1990s, so software packages for it are easy to find and use.

“It's been developed in the 1990s, so packages are easy to find, they're easy to implement.”

Making Sense (J.P. Morgan) · 0:23:27

Peng Cheng describes a nonlinear relationship in which equity returns are good in low volatility, decline as volatility rises, and may recover at extreme volatility.

“in periods of low volatility, equity returns are probably good, right? But as volatility picks up, then equity returns declines.”

Making Sense (J.P. Morgan) · 0:23:55

Peng Cheng says a support vector machine delivered much better out-of-sample performance than several other models when predicting equity futures returns from historical volatility.

“by using SVM, It actually produces much better out-of-sample performance than a number of other machine learning models.”

Making Sense (J.P. Morgan) · 0:24:26

Peng Cheng says support vector regression is computationally heavy and does not scale well to large problems.

“it's very computationally heavy, and it doesn't really scale well to large problems.”

Making Sense (J.P. Morgan) · 0:24:26