← Back
Evidence source 5243Spot Checked

Forecasting Cryptocurrency Returns from Sentiment Signals: An Analysis of BERT Classifiers and Weak Supervision

Unknown venue2022-04-06Paper
Executive summary

Analyzes BERT classifiers and weak supervision for predicting cryptocurrency returns using sentiment from news and social media.

What it examines

This paper examines the impact of sentiment from news and social media on predicting cryptocurrency prices using machine learning models, specifically BERT classifiers and weak supervision. It focuses on Bitcoin and Ethereum, aiming to enhance forecast accuracy and trading decisions.

What it concludes

The research highlights the potential of weak supervision and sentiment analysis in improving cryptocurrency forecasts. Future research could explore other financial markets and refine sentiment aggregation methods. Applications include better trading strategies and financial decision-making tools.

Extracted from this source

Evidence objects

Evidence 439572% extraction confidence
The research highlights the potential of weak supervision and sentiment analysis in improving cryptocurrency forecasts. Future research could explore other financial markets and refine sentiment aggregation methods. Applications include better trading strategies and financial decision-making tools.

key_findings bullet 1 · key_findings · validation V0

Raw abstract and provenance

Abstract: Anticipating price developments in financial markets is a topic of continued interest in forecasting. Funneled by advancements in deep learning and natural language processing (NLP) together with the availability of vast amounts of textual data in form of news articles, social media postings, etc., an increasing number of studies incorporate text-based predictors in forecasting models. We contribu… ▽ More Anticipating price developments in financial markets is a topic of continued interest in forecasting. Funneled by advancements in deep learning and natural language processing (NLP) together with the availability of vast amounts of textual data in form of news articles, social media postings, etc., an increasing number of studies incorporate text-based predictors in forecasting models. We contribute to this literature by introducing weak learning, a recently proposed NLP approach to address the problem that text data is unlabeled. Without a dependent variable, it is not possible to finetune pretrained NLP models on a custom corpus. We confirm that finetuning using weak labels enhances the predictive value of text-based features and raises forecast accuracy in the context of predicting cryptocurrency returns. More fundamentally, the modeling paradigm we present, weak labeling domain-specific text and finetuning pretrained NLP models, is universally applicable in (financial) forecasting and unlocks new ways to leverage text data. △ Less

Source row: 892 · abstract type: unknown