In the previous article, I went over how to create a trading environment using the generic components provided in the TensorTrade library. This article will focus on how to tune, train, and evaluate an agent over the built environment while also showing how to make custom models and action distributions in Ray. Without further delay, let’s start with building the model and action distribution!

Ray Components

When working with RL environments, it's convenient to customize different components of the training process. This is due to the type of data the environment might produce, the preprocessing needed before an agent receives an observation…

In this article, I’m going to make a different type of algorithm in TensorTrade. As the title suggests, I’ll be implementing an environment that reallocates funds within a portfolio of assets at every time step. In my previous article, I used sine curves to check whether the environment actually achieves the desired goal. I’m going to take a similar approach here; however, I’ll be adding more complexity to the price curves by injecting some randomness into the equation. There are many topics to cover in this series, so let’s get started!

“No wise man tries every day what he has…

Decision Making with Aspect-Based Sentiment Analysis using Transformers.

In the last article, I trained a model on the ABSA task from the SemEval-2014 dataset and analyzed its performance, speed, and behaviors. This article details how I use this model to choose a restaurant to dine at from the Yelp dataset. Without further delay, let’s get started!

Yelp Dataset

We can download the Yelp dataset in one of two ways:

The first requires signing an agreement with Yelp, after which the dataset can be downloaded as a zip file. The Kaggle method requires an account with a username and API key setup locally at ~/.kaggle/kaggle.json. …

Decision Making with Aspect-Based Sentiment Analysis Using Transformers.

We’ve all been in this situation before: looking up reviews for some new product we are interested in or some restaurant we’ve wanted to try. We glean information from one review to the next, each one rendering a more precise representation of the product. We keep scrolling and scrolling when suddenly an hour has passed, and we are no closer to an answer than we were before. We realize this a futile endeavor and that we’ll be searching endlessly for the decisive factor in determining how we spend our hard-earned money. Well, in this tutorial, I’m going to put this…

In this tutorial, I’m going to show how to use Ray with TensorTrade (TT) in order to create a profitable algorithm on a predictable sine curve. You may be asking yourself, why use something so simple when the real world is much more difficult to predict? This is a very good question, and there is a simple answer.

“The man who moves a mountain begins by carrying away small stones.”

Before trying to jump into the world of complex trading environments, a simple sine curve can be used to perform a sanity check on your trading algorithm. The…

Matthew Brulhardt

MS in Applied Mathematics and Statistics @ Stony Brook University | I’m a simple person who likes four things: design, mathematics, computer science, and data.

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