Making Good on LSTMs Unfulfilled Promise

11/11/2019
by   Daniel Philps, et al.
24

LSTMs promise much to financial time-series analysis, temporal and cross-sectional inference, but we find 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; which memory did what and when. This work has implications for many financial applications including to 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 LSTM and a simple sliding window learner (feed-forward neural net (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 learner, allowing testing of LSTM and sliding window (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-encoder (AE) and a novel hybrid approach, warp-AE. We find CLA out-performs simple LSTM and FFNN learners and CLA based on a sliding window (CLA-FFNN) out-performs a LSTM (CLA-LSTM) implementation. While for memory-addressing, ED under-performs DTW and AE but warp-AE shows the best overall performance in a real-world financial task.

READ FULL TEXT
research
12/06/2018

Continual Learning Augmented Investment Decisions

Investment decisions can benefit from incorporating an accumulated knowl...
research
12/06/2018

Continuous Learning Augmented Investment Decisions

Investment decisions can benefit from incorporating an accumulated knowl...
research
12/18/2018

A Comparison of LSTMs and Attention Mechanisms for Forecasting Financial Time Series

While LSTMs show increasingly promising results for forecasting Financia...
research
05/10/2022

Real-time Forecasting of Time Series in Financial Markets Using Sequentially Trained Many-to-one LSTMs

Financial markets are highly complex and volatile; thus, learning about ...
research
08/18/2020

Selecting Data Adaptive Learner from Multiple Deep Learners using Bayesian Networks

A method to predict time-series using multiple deep learners and a Bayes...
research
08/21/2023

Real World Time Series Benchmark Datasets with Distribution Shifts: Global Crude Oil Price and Volatility

The scarcity of task-labeled time-series benchmarks in the financial dom...
research
11/22/2012

Optimally fuzzy temporal memory

Any learner with the ability to predict the future of a structured time-...

Please sign up or login with your details

Forgot password? Click here to reset