City Research Online

Making Good on LSTMs' Unfulfilled Promise

Philps, D., Garcez, A. and Weyde, T. ORCID: 0000-0001-8028-9905 (2019). Making Good on LSTMs' Unfulfilled Promise. Paper presented at the NeurIPS 2019 Workshop on Robust AI in Financial Services: Data, Fairness, Explainability, Trustworthiness, and Privacy, 13 Dec 2019, Vancouver, Canada.

Abstract

LSTMs promise much to financial time-series analysis, temporal and cross-sectional inference, but we find that they do not deliver in a real-world financial management task. We examine an alternative called Continual Learning (CL), a memory-augmented approach, which can provide transparent explanations, i.e. which memory did what and when. This work has implications for many financial applications including credit, time-varying fairness in decision making and more. We make three important new observations. Firstly, as well as being more explainable, time-series CL approaches outperform LSTMs as well as a simple sliding window learner using feed-forward neural networks (FFNN). Secondly, we show that CL based on a sliding window learner (FFNN) is more effective than CL based on a sequential learner (LSTM). Thirdly, we examine how real-world, time-series noise impacts several similarity approaches used in CL memory addressing. We provide these insights using an approach called Continual Learning Augmentation (CLA) tested on a complex real-world problem, emerging market equities investment decision making. CLA provides a test-bed as it can be based on different types of time-series learners, allowing testing of LSTM and FFNN learners side by side. CLA is also used to test several distance approaches used in a memory recall-gate: Euclidean distance (ED), dynamic time warping (DTW), auto-encoders (AE) and a novel hybrid approach, warp-AE. We find that ED under-performs DTW and AE but warp-AE shows the best overall performance in a real-world financial task.

Publication Type: Conference or Workshop Item (Paper)
Publisher Keywords: Continual learning, time-series, LSTM, similarity, DTW, auto-encoder
Subjects: H Social Sciences > HG Finance
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments: School of Mathematics, Computer Science & Engineering > Computer Science
URI: https://openaccess.city.ac.uk/id/eprint/23682
[img]
Preview
Text - Accepted Version
Download (493kB) | Preview

Export

Downloads

Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login