Predictive Strength
unravel
unravel
Predictive Strength
Measures the ratio of positive to negative mentions across all tracked channels.
Crypto markets exhibit faster price discovery than traditional assets, with social sentiment shifts often preceding technical indicators. The University of East London study found Twitter sentiment data improved Bitcoin price prediction accuracy to 81% when combined with on-chain metrics. This lead-lag relationship stems from retail traders vocalizing positions before executing trades.
Crypto's retail-dominated markets magnify behavioral biases. The Fear and Greed Index demonstrates how sentiment extremes (<20 = fear, >80 = greed) reliably mark local price bottoms/tops. Aggregate Sentiment quantifies these crowd psychology patterns, identifying when FOMO or panic selling reaches critical mass.
Aggregate sentiment data is sourced from Telegram, Youtube and major news portals, followed by preprocessing and analysis via machine learning models. The raw sentiment scores are then normalized against historical averages to create a relative index.
unravel
To understand a predictive factors predictive power, we create a simple long/short strategy and simulate its past performance (with daily rebalancing):
The strategy is rebalanced daily, on a continuous basis. There are 0.5% transaction costs applied on each position adjustment.
Get started by validating the historical performance of the strategy with our transparent code snippets.
Copy and paste the code snippets below into your Python environment or download the files below.
Predictive Strength
Predictive Strength
Predictive Strength
Predictive Strength