The AI and big data revolution have energized the financial market in ways not seen since the introduction of electronic trading in the 1980’s.
The concept behind deep learning is surprisingly easy to understand. Through thousands of iterations of trial and error, artificial neural networks are able to classify profitable states of a tradable asset as measured through a compilation of data signals.
The question remains: With the influx of new alternative data sources flooding the market, how can one measure the efficacy of an alternative data signal?
Join Lucena Research CEO Erez Katz for an unveiling of an innovative investment approach. Erez will provide an overview of Lucena’s machine learning and data validation process. He will then dive into how we have automated the ingestion, validation and enhancement of an alternative data source for forecasting asset prices and KPIs.
No data science or deep learning experience required for this session.
“The Journey of an Alternative Data Signal” Video Will Cover:
- – Trends in Alternative Data and quantitive investment research.
- – A deep dive into the data validation process.
- – Why feature selection and engineering is critical for success.
- – How deep learning and convolutional neural networks are used to forecast stock prices and KPIs.
- – How empirical evidence of alternative data’s value can be discovered along with supporting materials
- – Live Q&A
Whether you’re an investment professional looking to utilize Alternative Data for decision making or a data provider looking to maximize your data’s monetization potential in the financial markets this discussion has something for you. Enjoy!
Additional Resources:
Brochure: How to find short only signals with Wall Street Horizon’s data.
Video: How to Forecast Securities Using Neural Networks
Video: Constructing Unique Data Feeds for Stock and KPI Forecasting
Webinar with Co-Founder Dr. Tucker Balch: Applying Deep Reinforcement Learning to Trading
Blog Post: How Machine Learning Can Validate Data for Stock Forecasting