Emotion AI for Market Prediction | Hume Blog | Hume AI

About MoodMetrics

MoodMetrics AI is revolutionizing financial markets by decoding the emotional undercurrents in central bank communications. Founded in 2024 at the University of Bath, the company empowers financial institutions with emotional intelligence insights by analyzing verbal and non-verbal behavior, including vocal tone, speech patterns, and micro-expressions.

By integrating Hume’s Expression Measurement API, MoodMetrics detects subtle emotional cues that traditional models miss—helping investment banks, retail banks, and hedge funds anticipate market movements with greater precision. The company has been nationally recognized through awards such as the Santander UK University Startup Grant and a Sparkies Award nomination.

The Challenge

Traditional sentiment analysis tools rely heavily on text, leaving out emotional context such as vocal stress, tone shifts, and facial micro-expressions. MoodMetrics set out to solve several limitations in market analysis:

• Text-Only Limitations: Most models miss non-verbal signals critical to interpreting central bank communications.
• Missed Emotional Cues: Policymakers may express stress or uncertainty through tone or facial expressions that don’t appear in written transcripts.
• Reduced Forecasting Power: Without these cues, models may lag behind actual market sentiment.

The Solution: Decoding Emotion with Hume’s Expression Measurement API

MoodMetrics integrated Hume’s Expression Measurement API to enhance its predictive models with multimodal insights:

• Speech and Tone Analysis: Hume’s API helps identify stress and confidence levels in central bank speeches, offering earlier insights into hawkish or dovish sentiment.
• Micro-Expression Recognition: Subtle facial expressions, often overlooked in traditional tools, are analyzed to detect underlying emotion and intent.

Results

• 67% prediction accuracy in a proof-of-concept following a Jerome Powell FOMC speech
• Faster signal detection by integrating non-verbal cues with historical market data
• Smooth implementation of the Expression Measurement API, with issues quickly resolved through collaboration with Hume’s support team on Discord
• Positive feedback from early users across finance, healthcare, defense, and marketing

For more information on how empathic AI can enhance your digital solutions, please contact Hume AI.