On the Laravel News site there's a post showing an application of the IBM Watson Personality Insights service to discover trends and make predictions about future actions/preferences. They also show how to integrate it into your Laravel-based application thanks to this package.

One of the most important things as a business owner is being able to understand your customers’ needs and wants; such that you are able to offer them a personalized experience. This works great if you know your customers on a personal level, but what if you don’t?

[...] Sure you could send out a survey from your site, then collect a huge amount of data, then process, analyze and finally being able to tell what package fits which user. This seems tiresome and plus people’s tastes and preferences change over time and you would have to repeat this process over and over again each time you want to offer them something new. There has to be a better way, and there is.

The post talks about the services offered by IBM Watson and, more specifically, about Personality Insights. They cover some about what this service offers as related to web preferences and link to a demo application you can use to get more context about its handling. The post wraps up showing how to integrate the package into your application and working with requests/responses to the IBM Watson Personality Insights service.

In the latest tutorial posted to the SitePoint PHP blog author Wern Ancheta shows you how to integrate your application with the Microsoft Text Analytics API, a service offered by the company putting machine learning to work on things like keyword extraction, topic detection and language detection.

With the explosion of machine learning services in recent years, it has become easier than ever for developers to create “smart apps”. In this article, I’ll introduce you to Microsoft’s offering for providing machine-learning capabilities to apps. Specifically, you’ll learn about the Text Analytics API and build an app to enhance the understanding of online sellers when it comes to their customers.

The tutorial then introduces the Microsoft Cognitive Services API and, more specifically, the Text Analytics API that they'll be hooking the application in to. They walk you through getting an API key for the service, creating an "account" for the application you're working with and deploying it for immediate use. They introduce the functionality of the API with a few "play" examples of each API offered before getting into the creation of their sample application - a tool that reviews the contents of customer feedback, looking for key phrases and returns highlighted versions with what it sees as important.

On the SitePoint PHP blog they've posted a tutorial showing you how to use the Prediction.IO server to create a movie recommendation application. Prediction.io is "an open source Machine Learning Server built on top of state-of-the-art open source stack for developers and data scientists create predictive engines for any machine learning task".

In this tutorial, I’m going to walk you through PredictionIO, an open-source machine learning server, which allows you to create applications that could do the following: recommend items (e.g. movies, products, food), predict user behavior, identify item similarity and rank items.

You can pretty much build any machine learning application with ease using PredictionIO. You don’t have to deal with numbers and algorithms and you can just concentrate on building the app itself.

The tutorial, the first part of a series, refreshes some older instructions for getting the Prediction.IO system up and running. He walks you through the creation of an AWS instance for the server a few different ways (Vagrant, Docker, etc). He then talks about the use of the Movie API from MovieDB and the two parts of the application that will be implemented on top of it: a learning phase and a recommendation phase. They show how to use Prediction.io to create the recommendation engine and make the new application on top of it. He helps you install some dependencies to use in the PHP side of the application and briefly explains what they're for.

This wraps up part one of the series. In the second part he starts putting this all to use and creates the PHP functionality to lay on top of the machine learning engine and handle learning and recommendations for users.