Predicting Profitability: Introducing PredictNow.Ai a Live Machine Learning Tool to Alpaca

By Ernest Chan

What is PredictNow.Ai? is a no-code machine learning SaaS-based in Toronto, Canada that is primarily focused on helping traders apply machine learning to their investment strategies in order to predict the profitability of their next trade. can calculate the most important input variables groups (also known as “clusters”) that empower a user’s prediction and only incorporate those in the prediction decision.

Users have to train a machine learning model based on their historical results, where they receive predictive performance results for both the in-sample and out-of-sample datasets. This trained model is then downloaded and is used in the Live section. In the Live section, users upload the model file along with the data features for that day into the software. The software then utilizes the previously trained model to provide a prediction for the daily dataset. We also provide access to a Rest API, allowing the user to directly implement the software into their internal processes.

This no-code process can help traders predict the profitability of their trades and help improve their existing trading strategies.

How to sign up for PredictNow.Ai and link an Alpaca brokerage account?

If you are an existing Alpaca user linking to is quite simple. Go to the website and sign up for an account. You can initially get full access through a 30 day free trial. Once this is done on the PredictNow platform you will see an option to sign in to Alpaca.

As soon as you’re logged in you will receive an authentication page asking for your permission to allow PredictNow to access the relevant information. As soon as you click allow it will take you back to the train mode page on PredictNow.Ai.

How to use PredictNow.Ai with Alpaca Data?

Once you’ve given permission to the platform your brokerage data can be directly imported from Alpaca to currently offers Alpaca users two Profit and Loss or PNL modes to choose from.

One is the round-trip PnL. A round trip would basically be taking a long version and selling it or taking a short version and buying it later. For each of the entries for the realized round-trip PnL the associated time stamp is the trade entry time stamp.The second PnL is the MTM or mark to market is basically one entry for each business day and this illustrates the change in NAV on a day to day basis.

Users will first work in train mode to create a model using training data and once the model is complete and you are satisfied with probability analysis you can go ahead and download the model and upload it into the live mode.

Attached here is a demo which walks you through how to link your Alpaca data to PredictNow and how to train and use the live modes. This demo will also go into detail regarding which results are relevant and what specific data sheets indicate.

If you have any questions or trouble setting up, please do not hesitate to reach out to us at Our team also offers professional consulting services and are happy to guide you through setting up a successful model to further improve your trading strategy.

For more information about our work, visit

About the Author: Ernie is a noted quantitative hedge fund manager and quant finance author. Previously he has applied his expertise in machine learning IBM T.J. Watson Research Center’s Human Language Technologies group, at Morgan Stanley’s Data Mining and Artificial Intelligence Group, and at Credit Suisse’s Horizon Trading Group.

Financial Machine Learning SaaS that enables traders to apply machine learning predictions to their investment decisions.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

What Gordon Ramsay Taught Me About Data Visualization

An apple salad garnished with herbs, red onions and cheese served on a white plate

Daily Data Science Tip #12

How to hide a dramatically strengthening USS pension scheme in six easy steps

How to set up Analytics Dashboards for your Marketing Teams

The Day You Became a Kaggler: Part II Why, What and How of the Outliers!

CDO Panel discussion at SAS Forum

Geo-Spatial Data Mining: How AI can transform the very bedrock of business strategy and operations

Descriptive Statistics Basics.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store

Financial Machine Learning SaaS that enables traders to apply machine learning predictions to their investment decisions.

More from Medium

Understanding Financial Feature Importance

Time Series Modeling and Deep Reinforcement Learning (DRL) on High-Frequency Crypto Exchange Data

Sensorial-based ML Applications in Modern Industrial Product-Lines

Utilizing Long Short-Term Memory Networks to Forecast the Price of Bitcoin in R