Model Misfires Raise Questions Over Training Data
Quants wrestle with how far into the past their machine learning models should peer.
Wisdom accumulated over many decades is highly prized in most cultures. Less so for machine learning in investing, it would seem.
Algorithms that use long histories of data to build their understanding of markets flopped during the Covid-19 pandemic. Such models failed “pretty spectacularly” in the extreme events of 2020, says Michael Heldmann, head of multi-factor equity investing for North America at Allianz Global Investors, citing research conducted by the firm.
“They have been hammered
Only users who have a paid subscription or are part of a corporate subscription are able to print or copy content.
To access these options, along with all other subscription benefits, please contact info@waterstechnology.com or view our subscription options here: http://subscriptions.waterstechnology.com/subscribe
You are currently unable to print this content. Please contact info@waterstechnology.com to find out more.
You are currently unable to copy this content. Please contact info@waterstechnology.com to find out more.
Copyright Infopro Digital Limited. All rights reserved.
As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (point 2.4), printing is limited to a single copy.
If you would like to purchase additional rights please email info@waterstechnology.com
Copyright Infopro Digital Limited. All rights reserved.
You may share this content using our article tools. As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (clause 2.4), an Authorised User may only make one copy of the materials for their own personal use. You must also comply with the restrictions in clause 2.5.
If you would like to purchase additional rights please email info@waterstechnology.com
More on Data Management
It’s just semantics: The web standard that could replace the identifiers you love to hate
Data ontologists say that the IRI, a cousin of the humble URL, could put the various wars over identity resolution to bed—for good.
The art of communication: Data pros need better messaging
As the CDO of a tier-one bank puts it, when there’s an imbalance in communication between the data organization and the business (much less other technology heads) “that creates problems.”
Does TP Icap-AWS deal signal the next stage in financial cloud migration?
The IMD Wrap: Amazon’s deal with TP Icap could have been a simple renewal. Instead, it’s the stepping stone towards cloudifying other marketplace operators—and their clients.
T. Rowe Price’s Tasitsiomi on the pitfalls of data and the allures of AI
The asset manager’s head of AI and investments data science gets candid on the hype around generative AI and data transparency.
Waters Wavelength Ep. 298: GenAI in market data, and everything reference data
Reb is back on the podcast to discuss licensing sticking points for market and reference data.
Back to basics: Taxonomies, lineage still stifle data efforts
Voice of the CDO: While data professionals are increasingly showing their value when it comes to analytics and AI adoption, their main job is still—crucially—getting a strong data foundation in place. That starts with taxonomies and lineage.
Too ’Berg to fail? What October’s Instant Bloomberg outage means for the industry
The ubiquitous communications platform is vital for traders around the globe, especially in fixed income and exotic derivatives. When it fails, the disruption can be great.
J&J debuts AI data contracts management tool
J&J’s new GARD service will use AI to help data pros query data contracts and license agreements.
