---
title: Transfer Learning for Data-Scarce ML
url: https://www.ml-quant.com/papers/repec/cup-polals-v-32-y-2024-i-1-p-84-100-6/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: RePEc:cup:polals:v:32:y:2024:i:1:p:84-100_6
source_url: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fwww.cambridge.org%2Fcore%2Fproduct%2Fidentifier%2FS1047198723000207%2Ftype%2Fjournal_article%3Bh%3Drepec%3Acup%3Apolals%3Av%3A32%3Ay%3A2024%3Ai%3A1%3Ap%3A84-100_6
featured: 2024-09-05
citations: unknown
topic: ML & AI Methods
---


# Transfer Learning for Data-Scarce ML

Deep transfer learning models like BERT can greatly enhance the analysis of large political text corpora in social sciences research by reducing the need for extensive manually annotated training data.

- Source: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fwww.cambridge.org%2Fcore%2Fproduct%2Fidentifier%2FS1047198723000207%2Ftype%2Fjournal_article%3Bh%3Drepec%3Acup%3Apolals%3Av%3A32%3Ay%3A2024%3Ai%3A1%3Ap%3A84-100_6
- Identifier: RePEc:cup:polals:v:32:y:2024:i:1:p:84-100_6
- Released: 2024-09-05
- First featured: Quant Letter No. 64 (2024-09-05): https://www.ml-quant.com/issues/2024-09-05/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: ML & AI Methods

## Related

- [Machine Learning for Synthetic Data Generation: a Review](https://www.ml-quant.com/papers/arxiv/2302.04062/): A Review: The article reviews machine learning models for creating synthetic data, discussing their uses, methods, privacy issues, fairness, and future research opportunities in fields like computer vision, speech, natural language processing, healthcare, and business.
- [Business Intelligence through Artificial Intelligence: A Review](https://www.ml-quant.com/papers/ssrn/4831916/): A Review: The article reviews the incorporation of AI in business intelligence, focusing on AI-powered data analytics, natural language processing, and big data integration, and how this can improve data visualization and decision-making.
- [Quantifying A Firm's AI Engagement: Constructing Objective, Data-Driven, AI Stock Indices Using 10-K Filings](https://www.ml-quant.com/papers/doi/10-1016-j-techfore-2024-123965/): A new method using natural language processing (NLP) has been suggested for classifying AI stocks, providing a cost-effective alternative that outperforms existing AI-themed ETFs.
- [Neuradicon: Operational representation learning of neuroimaging reports](https://www.ml-quant.com/papers/arxiv/2107.10021/): Learning Neuroimaging Reports: Neuradicon, a new natural language processing framework, has been developed for analyzing neuroradiological reports, showing excellent adaptability across different time periods and healthcare institutions.
- [Artificial Intelligence in Tax Administration: Enhancing Compliance, Transparency, and Ethical Governance](https://www.ml-quant.com/papers/ssrn/5285760/): The article discusses the potential of AI, particularly NLP, ML, and intelligent chatbots, to improve tax administration, while also considering the ethical and regulatory challenges of AI deployment.
- [Disruptive Innovation and IPO Outcomes: Evidence from Machine Learning](https://www.ml-quant.com/papers/ssrn/4556095/): The paper presents a new text-based measure of disruptive innovation, developed through machine learning and textual analysis of IPO prospectuses, which accurately predicts IPO results and challenges the hype hypothesis about tech stocks.