PredictNow

Our Approach

See below to learn about the techniques and strategies PredictNow.ai employs to achieve the most accurate results possible on all predictions.

Conditional Portfolio Optimization

Our patent pending technology can automatically optimize your portfolio's capital allocations to the current market regime. For further information, please see our blog post:

Risk Management via Corrective AI

The PredictNow.ai software uses machine learning models to determine the Probability of Profit for a trade, plus it can allocate capital and manage risks accordingly. This quantamental strategy applies machine learning to help discretionary or fundamental investment managers quantify and systematize their ideas, factors, and knowledge, all without the necessity of disclosing the fundamental strategy to a consultant. For more information on this topic, see Dr. Chan's presentation:

Explainable AI & Features Selection

The PredictNow.ai technology uses the cluster-based MDA method to perform features importance ranking and selection. We use this method as it gives the most interpretable and stable results for our users. For more information on this method, see our paper:

Pre-Engineered Features

With our 600+ pre-engineered features, users can generate predictive performance results for in-sample and out-of-sample datasets. For more information on these features, see our blog post:

User Manual

PredictNow.ai allows users to apply machine learning predictions to their data without any previous programming knowledge. All you need is an Excel (.xlsx) or csv file (.csv) with multiple columns of “predictor” variables and a single column with a “target” variable. (See our “Get Database” tab at the top of the screen to download our example files).

Our software will learn from the uploaded predictors-target pairs and make predictions on the unseen live data supplied via the Excel or csv file. It will also show you the performance metrics of the model (e.g. how accurate the predictions are). PredictNow.ai can predict either discrete target variables such as the sign of returns, or continuous variables such as the returns themselves.

NOTE: The program allows both .csv files and .xlsx files to be processed. However, when modifying/creating a csv file via Excel, some characters in the current file may not be correctly converted to .csv. We encourage Excel users to save their files to .xlsx, rather than .csv.

Interested in our API specifications?

Want to backtest your strategy?

Need help? Email our support team!