Dashboard Documentation

Although the BigML platform is very intuitive and easy to use, a little extra hand is always welcome! All these documents will help you understand how BigML works using our Dashboard. Applying the right features with the proper parameters will definitely help you build a robust and accurate predictive model to achieve the best results for your predictions.

Download full documentation

Sources

Importing and Preparing your Data

This document describes sources in detail. Discover the large variety of file formats and field types supported by BigML, and explore all the configuration options available. Learn how to prepare your data, upload it to BigML, and sync your account with several cloud repositories.

Datasets

Getting your Data Ready for Machine Learning

Get essential data statistics and visualize your data in a Scatterplot chart. Perform an infinite number of transformations to easily filter and add new fields to your dataset. Having important features is key to building robust predictive models.

Classification and Regression

Building Supervised Models and Making Predictions

Learn the complete process from building a classification and a regression model to making predictions with it. BigML provides decision trees, ensembles, logistic regressions, and deepnets for a wide range of use: from churn, loan, risk or sentiment analysis to patient diagnosis and more. Interpret the results with the powerful visualizations that BigML offers.

Object Detection

Perform object detection models

Learn how to use the BigML Dashboard to configure, visualize, and interpret this model and use it to make predictions.

Time Series

Forecasting your time-based data

Make forecasts based on the previously observed patterns in your time series data. This method is widely used for forecasting sales, stock prices, website traffic, predictive maintenance, production and industrial use cases among many others.

OptiML

Finding the Best Supervised Model Automatically

Get the supervised model that best fit your data with a single click. OptiML creates and evaluates hundreds of supervised models (decision trees, ensembles, logistic regression, and deepnets) with multiple configurations to finally return a list of the best models for your data. OptiML helps to avoid the difficult and time-consuming work of hand-tuning multiple supervised algorithms until you find the optimal one that solves your specific problem.

Cluster Analysis

Grouping your Data by Similarity

Segment your data by creating clusters and visualize your results in an interactive chart. This is instrumental for market and customer segmentation, portfolio management, and creating new features from your data while understanding its underlying structure.

Anomaly Detection

Detecting Unusual Instances

Find the top anomalous instances in your dataset and easily select or filter them. This technique is widely used for fraud detection, data cleansing tasks, predictive maintenance and intrusion detection, among others.

Association Discovery

Discovering Relevant Relationships

Discover valuable associations in your high-dimensional dataset while filtering out many deceptive associations. Some popular use cases are: market-basket analysis, recommendations, web usage pattern analysis, bioinformatics, incident detection, and digital forensics.

Topic Modeling

Finding Topics in Text Data

Uncover the hidden topics underlying a collection of documents and analyze the results with BigML's intuitive visualizations. Use your topics as final output for information retrieval tasks, collaborative filtering, or for assessing document similarity, among other use cases. You can also use those topics as input features to train other models.

PCA

Transform Your Datasets

Transform a dataset defined by possibly correlated variables into a set of uncorrelated variables with the goal of reducing the dataset dimensionality and/or exploring your data. PCA can be used in any industry vertical, however, it is typically applied in fields with high-dimensional data including bioinformatics, quantitative finance, and signal processing, among others.

Organizations

Collaborating within an Organization

Collaborate with other BigML users on the same projects, using the same Dashboard, but at different levels of privileges. Organizations are ideal for teams that need to work on the same Machine Learning models and share them with other external users.