---
title: Predicting Earnings Changes
url: https://www.ml-quant.com/papers/repec/bla-joares-v-60-y-2022-i-2-p-467-515/
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:bla:joares:v:60:y:2022:i:2:p:467-515
source_url: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fdoi.org%2F10.1111%2F1475-679X.12429%3Bh%3Drepec%3Abla%3Ajoares%3Av%3A60%3Ay%3A2022%3Ai%3A2%3Ap%3A467-515
featured: 2024-07-10
citations: unknown
topic: ML & AI Methods
---


# Predicting Earnings Changes

Machine learning models using extensive financial data can predict future earnings changes more accurately than traditional models and professional analysts.

- Source: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fdoi.org%2F10.1111%2F1475-679X.12429%3Bh%3Drepec%3Abla%3Ajoares%3Av%3A60%3Ay%3A2022%3Ai%3A2%3Ap%3A467-515
- Identifier: RePEc:bla:joares:v:60:y:2022:i:2:p:467-515
- Released: 2022-11-10
- First featured: Quant Letter No. 56 (2024-07-10): https://www.ml-quant.com/issues/2024-07-10/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: ML & AI Methods

## Related

- [The Impact of the ESG Factor on Industrial Performance An Analysis using Machine Learning Techniques](https://www.ml-quant.com/papers/ssrn/4910370/): The study applies machine learning to explore the link between ESG performance and corporate earnings, using data from over 850 European and US firms from 2007-2021.
- [Can AI Replace Stock Analysts? Evidence from Deep Learning Financial Statements](https://www.ml-quant.com/papers/ssrn/4813310/): The article introduces a deep-learning AI model that surpasses human analysts in predicting stock prices a year ahead, using large data sets efficiently.
- [Learnings from Scaling Visual Tokenizers for Reconstruction and Generation](https://www.ml-quant.com/papers/arxiv/2501.09755/): The study reveals that scaling the decoder in auto-encoders, specifically the VisionTransformer architecture for Tokenization (ViTok), improves reconstruction performance and sets new standards for class-conditional video generation when combined with Diffusion Transformers.
- [Corporate Culture and Takeover Vulnerability: Evidence from Machine Learning and Earnings Conference Calls](https://www.ml-quant.com/papers/ssrn/4626185/): Research using machine learning indicates that the threat of hostile takeovers can significantly weaken a company's culture, supporting the managerial myopia hypothesis.
- [IPO Pricing Prediction with Lasso-Neural Networks](https://www.ml-quant.com/papers/ssrn/4990940/): A new model using Lasso neural networks has been developed to predict IPO pricing for Chinese companies, with retained earnings per share being a key factor.
- [A Yield-Based Asset Ratio to Boost Minimum Investment Returns](https://www.ml-quant.com/papers/ssrn/4746302/): The article proposes a strategy to improve weak medium-term returns in retirement portfolios by adjusting the stock percentage based on the earnings yield of stock and the current yield of bonds, with caution needed when stock prices exceed sustainable levels.