An automated adaptive trading system for enhanced performance of emerging market portfolios
Abstract One of the most notable developments in the asset management industry in recent decades has been the growth of algorithmic trading. At the same time, significant structural changes in the industry have occurred, with passive investing gaining momentum. The intersection of these two major tr...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-02-01
|
| Series: | Financial Innovation |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40854-025-00754-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract One of the most notable developments in the asset management industry in recent decades has been the growth of algorithmic trading. At the same time, significant structural changes in the industry have occurred, with passive investing gaining momentum. The intersection of these two major trends poses special challenges during market downturns, magnifying portfolio losses and leading to significant outflows. Emerging market (EM) investors have seen two major downturn events in the 2020s, namely the COVID-19 pandemic and the Russia-Ukraine conflict, both of which have strongly affected EM portfolios’ risk-return profiles and increased their correlations with their developed market counterparts, eliminating much or all of EMs’ diversification benefits. This has led to major capital outflows from EM countries, further destabilizing these fragile economies. Against this backdrop, we argue that capital need not exit these riskier markets during periods of turmoil and support this by developing a second-generation Automated Adaptive Trading System (AATS) back-tested on a relevant, diversified EM portfolio that tracks the Morgan Stanley Capital International (MSCI) Emerging Markets Index during a volatile period characterized by negative returns, high risk, and a high correlation with global markets for the buy-and-hold EM portfolio. The system incorporates an Autoregressive Moving Average-Generalized AutoRegressive Conditional Heteroskedasticity model that offers an interpretability advantage over machine-learning methods. The main strength of the AATS is its ability to allow the embedded hybrid forecasting model to adapt to the changing environments that characterize EMs. This is done by implementing a recursive window technique and running a user-specified fitness function to dynamically optimize the mean equation parameters throughout the lead time. Back-testing several configurations of the flexible AATS consistently reveals its superiority while assuring the robustness of the results. We conclude that with the right investment tools, EMs continue to offer compelling opportunities that should not be overlooked. The novel AATS proposed in this study is such a tool, providing active EM investors with substantial value-added through its ability to generate abnormal returns, and can help to enhance the resilience of EMs by mitigating the cost of crises for those countries. |
|---|---|
| ISSN: | 2199-4730 |