Where & When ft. Streamplate

How we’re building a universal recommendation system.

Image for post
Image for post

Modern apps work in the following hierarchy:

An app is a piece of software that is managed by the OS (Operating System) which manages the kernel — a portion of software that directly manages the hardware. This hierarchy describes how modern computers operate today on mobile and desktop environments.

Software today is mostly packaged into apps that become available via distribution channels like the App Store & Google Play. There’s an inherent fragmentation in a system like this — meaning each ‘service’ becomes encapsulated into app.

Streamplate’s vision has always been to serve choice. So we’ve been building a universal recommendation system that can underscore other apps and behave like a global binder for the user.

By developing a universal recommendation system we’ve been looking to show a user what they exactly want when they open the app. Initially we’re focusing on eating and drinking because of how emotional driven these decisions can be. Emulating emotional viscosity with paired contextual details is the cornerstone for proper simulation.

The idea is to then extend these insights across different industries so that Streamplate understands what a user wants at any moment in time. In short, we’re looking to reduce the amount of interaction needed to interact with virtual worlds.

The core of Streamplate is our recommendation system. This is an AI based program that generates real-time suggestions based on instantaneous user interaction. With only milliseconds to return a recommendation from a user’s request, there becomes a lot of moving parts that have to turn as fast as possible. Maintaining this complexity has meant we’ve had to refactor and rewrite parts of the codebase at times.

However, understanding users is only the first half, the remainder involves enabling users to action their choices. This means that Streamplate has to offer a host of features that empowers users across a range of scenarios. With that in mind, Streamplate is launching with:

And with that — this is where we are:

  1. All our features have been implemented,
  2. We’re finalising our AI-recommendation system. Specifically, finalising our caching and logging service to store locally useful data for users to improve latency.
  3. We’re finalising our iOS UI. Specifically, finalising our settings screen and our venue-searching interactions which we call ‘treeMap’.

When can users start downloading Streamplate?
Probably in a few days.

When will venues be connected to Streamplate?
Probably in a few weeks.

Is Streamplate a food ordering app?
Nope, it’s a universal recommendation system that’s going to initially recommend food services.

To double down on what we’re trying to do:

If Google is the engine for searching information, we want Streamplate to be the engine for choosing preference.

We want to predict your search query.

Written by

Electrical engineering/Neuroscience at University of Sydney. Aspiring neuro-trauma surgeon with a few software/hardware goals. www.streamplate.com

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