For the past few months at MLQ we've been working on an AI investment research platform that combines fundamentals, alternative data, and ML-based insights.
We're excited to announce that we're opening it up a private beta to a small number of users for testing and feedback in the coming weeks.
The platform combines fundamentals, alternative data, and ML-based insights for smarter trading and investing.
The platform features data for both crypto and equities.
Below we'll discuss a few of the data sources that are currently provided in more detail.
Note: the data below is sandbox data, i.e. not financial advice.
Our crypto dashboard features top lists, news sourced from 50+ sources, blockchain data, and ML-based insights from on-chain analysis.
This includes top lists based on:
- Market capitalization
- Top tier volume
- Top volume
Our crypto news data is sourced from 50+ publications and categorized as follows:
- Business News
- Technology News
- Markets & Trading
- Policy & Regulation
- Bitcoin News
- Altcoin News
Blockchain data is provided for 1000+ crypto assets, including:
- New Addresses
- Active Addresses
- Transaction Count
- Average Transaction Value
- Block Height
- Block Size
- and more
ML-Based On-Chain Analysis
Powered by IntoTheBlock, the data is sourced from an AI company that leverages machine learning and advanced statistics to extract intelligent signals for crypto-assets.
The trading signals include:
- New Network Growth
- Large Transactions
- In the Money
Our equities data ranges from financial news, fundamentals, alternative data, sentiment analysis, and ML-based estimates.
We currently support over 3000 US equities with the following fundamental data:
- Market News
- Company News
- Basic & Advanced Statistics
- Reported Financials
- Insider Transactions
- Fund & Institutional Ownership
The data providers use natural language processing algorithms to analyze text data for US equities and extract the following insights:
- Social sentiment
- News sentiment
- SEC filing sentiment
This data provides social sentiment data from StockTwits. Data is to be viewed as a daily value.
- Overall Sentiment: Number between -1 and 1 where -1 is most bearish and 1 is most bullish.
- Total Scores: Number of social data inputs to generate the sentiment value.
- Positive Sentiment: Percent of social messages with positive sentiment.
- Negative Sentiment: Percent of social messages with negative sentiment.
News sentiment for the past 7 and 30 days
The Brain Sentiment Indicator monitors the stock sentiment from the last 7 and 30 days of public financial news for ~5,000 US stocks.
The sentiment scoring technology is based on a combination of various natural language processing techniques. The sentiment score assigned to each stock is a value ranging from -1 (most negative) to +1 (most positive) and is updated daily.
SEC Filing Sentiment
SEC filing sentiment analysis includes:
Metrics about the language used in a company’s most recent annual or quarterly filings (10Ks and 10Qs). This includes metrics on the financial sentiment and the scores based on the prevalence of words in the statement categorized into four themes: constraining language, interesting language, litigious language, and language indicating uncertainty.
Similarity & Differences in Language Metrics
Compares sentiment and language metrics from the company’s most recent report (annual or quarterly) to the report from last year (10K) or the corresponding quarter the prior year (10Q).
The ML-based estimates we have includes the probability of an up or down move the next day, multi-day return estimates, and stock rankings.
Next Day Probabilities
Precision Alpha uses six months of closing-price measurements and the mathematics of machine learning to calculate exact, closed-form expressions for Market Probabilities, Market Energy, Market Power, Market Resistance, and Market Noise.
ML-based Return estimates
Brain Company’s Machine Learning proprietary platform is used to generate a daily stock ranking based on the predicted future returns of a universe of around 1,000 stocks over 2, 3, 5, 10, and 21 days.
The model implements a voting scheme of machine learning classifiers that non-linearly combine a variety of features with a series of techniques aimed at mitigating the well-known overfitting problem for financial data with a low signal to noise ratio. Calculation is done in the morning before market open.
ML-Based Stock Rankings
This data provider takes in over 200 factors and signals including fundamentals, pricing, technical indicators, and alternative data, and then uses an ensemble machine learning technique to analyze and rank stocks.
Want to be a beta tester?
We will be opening the platform up to a small number of users for feedback and testing in the next few weeks.
If you would like to apply to join the waitlist, please fill out the form below and we'll reach out to you shortly:
If you'd like to wait for our public release, you can simply sign up to our email list here.