OpenNashPodcasts

Person

Emma Wu

Emma Wu appears on the J.P. Morgan podcast Making Sense, in an episode called Data Assets & Alpha Group: Demystifying AI in the Financial Domain (Part 1). She explains machine learning terms, including regression, overfitting, regularization, random forests, boosting, stacking and hyperparameters.

She also describes work from 2022, when she says her team developed a currency model that uses foreign exchange options selectively in risk-off markets. According to Wu, the model started with about 30 signals, and linear models did worse than nonlinear ones, with higher tracking error and weaker explanatory power.

1 episodes · 12 quoted claims

Emma Wu says linear regression finds the best-fit line by minimizing the sum of squared differences between actual and predicted values.

“the model aims to find the best feed line that minimizes the sum of square differences between the actual and predicted values.”

Making Sense (J.P. Morgan) · 0:05:04

Emma Wu defines overfitting as a model that predicts its training data accurately but performs poorly on new data.

“there is a situation that the model gives accurate predictions for training data, but not for the new data.”

Making Sense (J.P. Morgan) · 0:05:34

Emma Wu explains that regularization adds penalties to a model's loss function to help prevent overfitting.

“regularization is like you add penalties to the loss functions”

Making Sense (J.P. Morgan) · 0:05:34

Emma Wu says ElasticNet combines the lasso and ridge penalties and is useful for large datasets with many features.

“ElasticNet combines the penalties of both Lussell and Rage so that it can be useful when the data set is large and when there are large numbers of features”

Making Sense (J.P. Morgan) · 0:08:47

Emma Wu says a random forest is essentially a collection of decision trees combined into one model.

“random forest is essentially a collection of decision tree”

Making Sense (J.P. Morgan) · 0:12:28

Emma Wu describes boosting as building models in sequence, where each new model emphasizes the errors of the previous one.

“the next model or the next member, when going into the model, consistently emphasized the error from the previous member or the model.”

Making Sense (J.P. Morgan) · 0:15:07

Emma Wu describes stacking as using the predictions of several different models as inputs to a final meta model.

“you assign a lead analyst that you trust most to take the predictions of each models as the input and make a meta model to make the final predictions.”

Making Sense (J.P. Morgan) · 0:15:44

Emma Wu's team developed a systematic tail-hedge late-cycle currency model that applies FX options selectively in risk-off markets.

“So last year, we developed a systematic tailhatch model to apply FX options selectively in risk of market and we call it a tailhatch late cycle currency model.”

Making Sense (J.P. Morgan) · 0:17:13

The FX tail-hedge model began with about 30 signals spanning value, momentum, swap rates and volatility factors.

“initially we start with a list of about 30 signals across different categories such as value, momentum, swap rates, and volve factors.”

Making Sense (J.P. Morgan) · 0:17:13

Emma Wu says that in the FX options model, linear models underperformed nonlinear ones, with higher tracking error and weaker explanatory power.

“we find that linear underperformed nonlinear models with a relatively higher tracking error and poor explanatory power.”

Making Sense (J.P. Morgan) · 0:18:25

Emma Wu says the support vectors in a support vector model are the data points closest to the decision boundary.

“the support vector term stands for the data points that closest to the decision boundary.”

Making Sense (J.P. Morgan) · 0:21:45

Emma Wu defines hyperparameters as settings chosen before training rather than learned from the data.

“Hyperparameters in machine learning are like settings on a recipe that you can adjust before cooking.”

Making Sense (J.P. Morgan) · 0:22:18