By Mahesh Kashyap
The purpose of OVTLYR is to create the best possible environment to refine and engage the wisdom of crowds without imparting “noise” from additional biases or herd-like behaviors.
Our process consumes both publicly available and non-personally identifiable data relevant to covered assets using a unique classification system to generate consolidated psychographic distributions, which can then be used to identify the propensities of an array of cognitive biases. The presence (or lack) of these biases are treated as variables to correct for irrationality within a deep game theory tensor. This model produces a discrete directional (appreciation/depreciation) probability, which is charted as an oscillator where low values represent overly “fearful” markets and higher values represent increasingly “greedy” ones.
After a prediction has been made, OVTLYR tracks each asset’s adjusted price action to identify correlations between what’s seen in the behavioral model and what’s realized on the market. These are displayed as a confirming heatmap, where red zones indicate price pullbacks with corroborating behavioral data and similarly blue zones represent run-ups.
As with any AI architecture, there’s a ton of math involved in our system. However, no traditional technical indicators or fundamental financial values are used in this process, as including them may inadvertently lead our members who rely on these sources to factor them into their considerations more than once.
Because no data should be interpreted in a vacuum, we are happy to provide additional information such as financial fundamentals and breaking news to help provide context to the behavioral analytics.
We build on data from the bottom-up so that you can have a
top-down view of when markets have been too fearful or too greedy.