Want us to keep you posted?
Join our newsletter to receive AI driven investment strategies and market trends.
Machine Learning
Blog posts, webinars and more for how machine learning can impact investment and validate trading strategies. Subscribe to our weekly newsletter to stay informed.
We are thought leaders & creators
We believe knowledge is best when shared
Select the type of resources you wish to explore:
- Ai Driven Investment Strategies
- Algorithmic Investing
- Alternative Data
- Backtest
- Big Data
- Company Blog
- Convolutional Neural Networks
- DAS
- Data Analytics Suite
- Data Matching Engine
- Data Provider
- Data Qualification Engine
- Data Science
- Data Validation
- Deep Learning
- DQE
- Erez Katz
- Event Analyzer
- Forecasting
- Hedger
- Investment Strategies
- Long and Short Strategies
- Machine Learning
- Model Portfolios
- Neural Networks
- Portfolio Optimization
- Predictive Analytics
- Press Release
- QuantDesk
- Quantitative Analysis
- Quantitative Investing
- Short Only Investment Strategies
- Stock Forecasting
- Stock Prices
- Strategy
- Tiebreaker
- Time Series Data
- Webinar Videos
The Science Behind Stop-Loss & Target Gain – Learn When to Exit a Position
Co-Authored by: Erez M. Katz (CEO & Co-Founder) and Stuart Colianni (Quant)
Selecting Features with Permutation Importance
Authored by: Stuart Colianni / Quantitative Analyst @ Lucena Research.
A Dynamic Labeling Approach for Financial Assets Forecasting
Authored by: Tarun Bhatia, Stuart Colianni, Taylor Korf, and Erez Katz
Clustering for more effective model training
Stuart Colianni, Quantitative Researcher at Lucena Research
Lucena Research and Equifax to Deliver Consumer Credit Data Offerings
Erez Katz, Lucena Research CEO and Co-founder Lucena teamed up with Equifax® to create predictive signals derived from consumer credit analysis for actionable investment deliverables.
Stock Forecasting with Transformer Architecture and Attention Mechanism
Erez Katz, Lucena Research CEO and Co-founder In our stock forecasting research, our goal is to identify meaningful patterns within a noisy construct of time series data.
Capsule Networks or CNNs: Which is best for stock predictions?
Erez Katz, Lucena Research CEO and Co-founder Here I’d like to touch on some of the main points that motivated us to explore CapsNet.
Capsule Networks: Next Gen Deep Learning Computer Vision for Stock Forecasting
Erez Katz, CEO and Co-founder of Lucena Research Capsule Networks are a fascinating, relatively new technology for image classification. Compared to CNNs, capsule networks have many benefits and phenomenal potential for image classification tasks, specifically time series forecasting.
Consumer Emotion Signals for Forecasting Tradable Assets
An Interview with Cognovi Labs How consumer behavior can provide signals for forecasting tradable assets. Announcing a new partnership with Cognovi Labs, a leader in consumer behavioral science powered by AI.
Forecasting KPI: Using ML and Big Data for Investment Decisions
Erez Katz, CEO and Co-founder For us at Lucena, applying machine learning to the financial markets has taken an interesting turn in recent years. In theory, fitting a model to historical time series data and forecasting a KPI should be similar to how…
Trending Topics in Alt Data and Machine Learning for Investment
Webinar Overview On June 13th we will host a webinar dedicated to an open Q&A surrounding trending topics in Alt Data, Machine Learning, and Data Science for Finance. An emerging and rapidly evolving technical domain can cause great confusion and…
Testing Multi-Factor Models in QuantDesk
Jonathan Moreland, Director of Research, InsiderInsights.com Jonathan Moreland discusses how Insider Intelligence has been proven most valuable using QuantDesk‘s multi-factor model.
How to fight the commoditization of Alt Data
Erez Katz, CEO and Co-founder Lucena Research The challenge of prolonging alternative data relevancy is on many data provider’s mind. Increased competition, and wide distribution could quickly turn into alpha decay and commoditization.
A Quantamental Approach Using Labeling for Stock Trading
One of our Quants, Tarun Bhatia, reviews Quantamental Investing and Labeling Techniques for ML in Finance.
Feature Engineering for Trading: Art or Science?
Erez Katz, CEO and Co-founder Lucena Research How Feature Engineering Extracts Signals from Data for Trading Those of us who work with big data and the applications of deep learning are often conflicted where human intellect is applied. Utilizing feature…
How to minimize overfitting in your quantitative investment research
Erez Katz, CEO and Co-founder Lucena Research How Cross-Validation and Grid Searching Strengthen Your Model As new datasets enter the predictive analytics world, streamlining their evaluation and deployment is becoming increasingly essential. Combining multiple, independent datasets into a single predictive model…
How Dynamic Models Prolong An Investment Strategy
Erez Katz, CEO and Co-founder Lucena Research The benefits of dynamic models and how they prolong your investment strategy in a volatile market. One of the biggest fallacies of quantitative strategy development is the belief that a successful model will…
Why You Should Be Using A Genetic Algorithm for Feature Selection
Why You Should Be Using a Genetic Algorithm (GA) for Feature Selection At Lucena, our goal is to democratize some of the best kept secrets in the Financial industry. Our team works to refute the “black-box” image often associated with…
Data Science: A Prerequisite To Machine Learning and Investment Research
Erez Katz, CEO and Co-founder of Lucena Research Is your data research ready? Here are several key concepts for quantitative investment research. Data science is the crucial first step before machine learning can be applied.
How To Avoid Missing The Obvious In Your Deep Learning Strategy
Erez Katz, CEO and Co-founder of Lucena Research In Deep Learning, Extracting The Right Insights Hinges On Several Key Steps. Here is how to form a thorough deep learning strategy for investment research. To illustrate, here are two examples that were…