Token Metrics Machine Learning

Machine learning and quantitative features of Token Metrics explained.

17 articles in this collection
Written by Aagam Jain, Jad Hajali, and Chase Allred

Crypto Portfolio Strategies: How to Invest in Cryptocurrency With AI

How Token Metrics uses AI to make you money

Written by Chase Allred
Updated over a week ago

How Token Metrics Uses AI

Guide on How Token Metrics uses Machine Learning

Written by Jad Hajali
Updated over a week ago

Price Predictions vs Monthly TA Trends

Differences between modeling of price predictions and scoring of monthly TA Trends

Written by Chase Allred
Updated over a week ago

Data Science and Machine Learning Terms

Mean Absolute Error (MAE)

An average of the absolute errors |ei| = |yi| - |xi|, where yi is the prediction and xi the true value.

Written by Aagam Jain
Updated over a week ago

Root Mean Square Error (RMSE)

The standard deviation of the residuals (prediction errors).

Written by Aagam Jain
Updated over a week ago

Correlation

A statistic that measures the degree to which two variables move in relation to each other.

Written by Aagam Jain
Updated over a week ago

Multi Layer Perceptron Model (MLP)

An MLP consists of at least three layers of nodes: an input layer, a hidden layer and an output layer.

Written by Aagam Jain
Updated over a week ago

Stacking

An ensemble learning technique that combines several machine learning techniques into one predictive model.

Written by Aagam Jain
Updated over a week ago

Loss Function

A method of evaluating how machine learning techniques work on the training data.

Written by Aagam Jain
Updated over a week ago

Back Propagation

An algorithm that looks for the minimum value of the error function in weight space.

Written by Aagam Jain
Updated over a week ago

Supervised Learning

The machine learning task of learning a function that maps an input to an output based on example input-output pairs.

Written by Aagam Jain
Updated over a week ago

Unsupervised Learning

A type of self-organized learning that helps find previously unknown patterns in data set without pre-existing labels.

Written by Aagam Jain
Updated over a week ago

Initial Population

The process begins with a set of random individuals which is called a Population.

Written by Aagam Jain
Updated over a week ago

Fitness Function

The fitness function determines the ability of an individual to compete with other individuals.

Written by Aagam Jain
Updated over a week ago

Selection

During each successive generation, a portion of the existing population is selected to breed a new generation.

Written by Aagam Jain
Updated over a week ago

Crossover

Crossover is used to combine the genetic information of two parents to generate a new offspring.

Written by Aagam Jain
Updated over a week ago

Mutation

The random change in the chromosome, which make the genes of children a little different from its parents.

Written by Aagam Jain
Updated over a week ago