Saved in:
Bibliographic Details
Main Authors: Varshavskiy, Ilyas, Boboeva, Bonu, Khalilbekov, Shuhrat, Azimi, Azizjon, Shulgin, Sergey, Nizamitdinov, Akhlitdin, Borde, Haitz Sáez de Ocáriz
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.09294
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915548343828480
author Varshavskiy, Ilyas
Boboeva, Bonu
Khalilbekov, Shuhrat
Azimi, Azizjon
Shulgin, Sergey
Nizamitdinov, Akhlitdin
Borde, Haitz Sáez de Ocáriz
author_facet Varshavskiy, Ilyas
Boboeva, Bonu
Khalilbekov, Shuhrat
Azimi, Azizjon
Shulgin, Sergey
Nizamitdinov, Akhlitdin
Borde, Haitz Sáez de Ocáriz
contents Machine Learning models in finance are highly susceptible to model drift, where predictive performance declines as data distributions shift. This issue is especially acute in developing economies such as those in Central Asia and the Caucasus - including Tajikistan, Uzbekistan, Kazakhstan, and Azerbaijan - where frequent and unpredictable macroeconomics shocks destabilize financial data. To the best of our knowledge, this is among the first studies to examine drift mitigation methods on financial datasets from these regions. We investigate the use of synthetic outliers, a largely unexplored approach, to improve model stability against unforeseen shocks. To evaluate effectiveness, we introduce a two-level framework that measures both the extent of performance degradation and the severity of shocks. Our experiments on macroeconomic tabular datasets show that adding a small proportion of synthetic outliers generally improves stability compared to baseline models, though the optimal amount varies by dataset and model
format Preprint
id arxiv_https___arxiv_org_abs_2510_09294
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mitigating Model Drift in Developing Economies Using Synthetic Data and Outliers
Varshavskiy, Ilyas
Boboeva, Bonu
Khalilbekov, Shuhrat
Azimi, Azizjon
Shulgin, Sergey
Nizamitdinov, Akhlitdin
Borde, Haitz Sáez de Ocáriz
Machine Learning
Machine Learning models in finance are highly susceptible to model drift, where predictive performance declines as data distributions shift. This issue is especially acute in developing economies such as those in Central Asia and the Caucasus - including Tajikistan, Uzbekistan, Kazakhstan, and Azerbaijan - where frequent and unpredictable macroeconomics shocks destabilize financial data. To the best of our knowledge, this is among the first studies to examine drift mitigation methods on financial datasets from these regions. We investigate the use of synthetic outliers, a largely unexplored approach, to improve model stability against unforeseen shocks. To evaluate effectiveness, we introduce a two-level framework that measures both the extent of performance degradation and the severity of shocks. Our experiments on macroeconomic tabular datasets show that adding a small proportion of synthetic outliers generally improves stability compared to baseline models, though the optimal amount varies by dataset and model
title Mitigating Model Drift in Developing Economies Using Synthetic Data and Outliers
topic Machine Learning
url https://arxiv.org/abs/2510.09294