Poster Session and Lunch
Monday, September 16, 2019 - 11:30am - 1:30pm
- Modeling Non-Normal Corporate Bond Yield Spreads by Copula
Jong-Min Kim (University of Minnesota, Morris)
This research focuses on modeling for how corporate bond yield spreads are affected by explanatory variables such as equity volatility, interest rate volatility, r, slope, rating, liquidity, coupon rate, and maturity. Therefore, we use the Gaussian copula regression method with Weibull marginal distributions and also employ several copula functions to test for the tail dependence between yield spreads and other explanatory variables. We show that our regression model is a better-fitting model than the one based on the lower AIC value. We find that (1) coupon rates increase noncallable bond yield spreads, while coupon rates do not affect callable bond yield spreads in the traditional regression and (2) stronger tail dependence in the joint upper tail for the relation between equity volatility and noncallable yield spreads, among others.
- Adaptive-Halting Policy Network for Early Classification
Thomas Hartvigsen (Worcester Polytechnic Institute)
Early classification of time series is the prediction of the class label of a time series before it is observed in its entirety. In time-sensitive domains where information is collected over time it is worth sacrificing some classification accuracy in favor of earlier predictions,ideally early enough for actions to be taken. However, since ac-curacy and earliness are contradictory objectives, a solution must address this challenge to discover task-dependent trade-offs. We design an early classification model, called EARLIEST, which tackles this multi-objective optimization problem, jointly learning (1) to classify time series and (2) at which timestep to halt and generate this prediction. By learning the objectives together, we achieve a user-controlled balance between these contradictory goals while capturing their natural relationship. Our model consists of the novel pairing of a recurrent discriminator network with a stochastic policy network, with the latter learning a halting-policy as a reinforcement learning task. The learned policy interprets representations generated by the recurrent model and controls its dynamics,sequentially deciding whether or not to request observations from future timesteps. For a rich variety of datasets (four synthetic and three real-world), we demonstrate that EARLIEST consistently out-performs state-of-the-art alternatives in accuracy and earliness while discovering signal locations without supervision.