×
BigML is working hard to support a wide range of browsers. Your experience will be better with:
Association Predictions: Association Sets
Jan2017
Image of Association Predictions: Association Sets

BigML is bringing predictions for Associations to the Dashboard. Association Sets allow you to pinpoint the items which are most strongly associated with your input data. For example, given a set of products purchased by a person, what other products are most likely to be bought?

All the predicted items will be ranked according to a similarity score, and they will be displayed in a table view. You can also visualize each predicted rule in a Venn diagram to get a sense of the correlation strength between the input data and the predicted items. Read more about Association Sets in the 8th chapter of the Associations documentation.

associations predictions itemsets association rules associationset
BigML Certifications
Jan2017
Image of BigML Certifications

We are happy to announce BigML Certifications, for organizations and professionals that want to master BigML to successfully deliver real-life Machine Learning projects. These courses are ideal for software developers, system integrators, analysts, or scientists, to boost their skill set and deliver sophisticated data-driven solutions. We offer two separate courses, each of them consisting of 4 weekly online classes of 3 hours each:

  • Certified Engineer: all you need to know about advanced modeling, advanced data transformations, and how to use the BigML API (and its wrappers) in combination with WhizzML to build and automate your Machine Learning workflows.

  • Certified Architect: learn how to implement your Machine Learning solutions so they are scalable, impactful, capable of being integrated with third-party systems, and easy to maintain and retrain.

If you successfully pass the certification exam, BigML will award you with a diploma. In addition, BigML Certified Partners will receive business referrals that help them source new Machine Learning projects.

courses modeling api supervised unsupervised whizzml data transformations engineer architect miscellaneous
Partial Dependence Plot for Ensembles
Dec2016
Image of Partial Dependence Plot for Ensembles

This new visualization for ensembles, commonly known as Partial Dependence Plot, allows you to visualize the impact that a set of fields have on predictions. You will be able to determine which fields are most relevant for ensemble predictions and how sensitive your ensemble predictions are to their different values.

The chart displays a heatmap representation of your predictions based on different values of the two selected fields in the axes regardless of the rest of the fields used to train your ensemble. You can select any categorical or numeric field for the axes and configure the values for the rest of the input fields by using the fields inspector panel on the right.

supervised classification regression visualization dashboard predictions ensemble
Batch Field Importances
Dec2016
Image of Batch Field Importances

This feature enables you to include the field importances in your batch predictions, i.e., a set of percentages indicating how much each field in your dataset contributed to the prediction of a given instance. You can include those values in your output file and dataset either with BigML Dashboard or the API. This will give you a better understanding of your predictions as it will reveal which are the most relevant fields factoring in a given prediction.

supervised predictions batch predictions regression classification models ensembles api dashboard prediction
Topic Distributions
Nov2016
Image of Topic Distributions

Topic Models assume that each document exhibits a mixture of topics. The main goal of creating a Topic Model is to discover the topic importances for a given document. For example, a document may be 70% about "Machine Learning", 20% about "stock market" and 10% about "startups".

Topic Distributions allow you to make predictions for a single data instance, and Batch Topic Distributions help predict the same for multiple instances simultaneously. Based on a given Topic Model, BigML Topic Distributions provide a set of probabilities for each data instance (one probability per topic), which indicate the relative relevance of all topics for that instance.

Learn more about Topic Models here

TopicModels TopicDistributions BatchTopicDistributions TopicProbabilities API Dashboard Fall2016 Unsupervised topicmodel
Topic Models
Nov2016
Image of Topic Models

The BigML team has brought Topic Models to the API and the Dashboard as part of the Fall 2016 release. Topic Models are an optimized implementation of Latent Dirichlet Allocation, a probabilistic unsupervised learning method that determines the topics underlying a collection of documents.

Topic Models' main application areas include browsing, organizing and understanding large amounts of unstructured text data, which can be very useful for information retrieval tasks, collaborative filtering or content recommendation use cases among others.

BigML provides two original visualizations that accompany its implementation so you can better inspect your Topic Model:

  • Topic Map: get an overview of your topic importances and their thematic closeness.
  • Term Chart: get an overview of the main terms that make up your found topics.
TopicModels Topics TermChart TopicMap API Dashboard Fall2016 Unsupervised topicmodel
2D Chart for Logistic Regression
Sep2016
Image of 2D Chart for Logistic Regression

BigML has released the 2D chart for Logistic Regression for you to analyze the impact of two input fields on predictions simultaneously. This view complements the current 1D chart for Logistic Regression. Just select any categorical or numeric field for the axis and the objective class probabilities will be automatically displayed in the heat map chart. You can also configure the rest of input field values using the fields form to the right. To learn more about Logistic Regression, see our Summer 2016 release.

logisticregression dashboard supervised algorithm classification summer2016
Sublime Text Package
Jul2016
Image of Sublime Text Package

Ease your WhizzML coding with syntax highlighting and auto-completion using the Sublime Text package. If you are a WhizzMLer and a Sublime Text fan, you will love this new package. Install it via Package Control.

whizzml source code scripts libraries sublime text
Field Codings for Logistic Regressions
Jun2016
Image of Field Codings for Logistic Regressions

Logistic regression needs numeric variables as input data. In order to support categorical fields, BigML transforms them by using one-hot coding, i.e., mapping to binary values (0s and 1s only). With Field Codings you can encode your categorical fields using three different strategies: dummy coding, contrast coding and other coding. Learn more about the three options in the Dashboard documentation.

logisticregression dashboard supervised categorical parameters
Individual Model Predictions for Ensembles
Jun2016
Image of Individual Model Predictions for Ensembles

Include all the individual trees predictions within the ensemble when creating a batch prediction. You can also include the confidence or expected error for each individual prediction by enabling the confidence option for the output file. This information will provide you a deeper understanding of the ensemble predictions and a flexible way to compute your preferred prediction combination.

batch prediction output settings single models predictions ensemble
Logistic Regression in your Dashboard
May2016
Image of Logistic Regression in your Dashboard

After bringing logistic regression to the API, it is now available in your Dashboard.

BigML is one of very few Machine Learning platforms offering a logistic regression visualization, which includes a twofold view: a chart and a coefficients table. The logistic regression chart provides a visual way to analyze the impact of your input fields on predictions. The table shows all the coefficients learned for each of the logistic function variables, which is ideal for inspecting model results and debugging tasks.

logisticregression dashboard supervised algorithm classification summer2016
Logistic Regression Predictions
May2016
Image of Logistic Regression Predictions

The ultimate goal of creating a logistic regression is to make predictions with it. Easily predict single instances using BigML prediction form —just input the values for the fields used by the logistic regression. You will get the predicted class along with its probability at the top of the view.

BigML also provides all classes probabilities in a visual histogram that changes real-time when you configure the input field values.

predictions logisticregression classification supervised dashboard summer2016
Logistic Regression Batch Predictions
May2016
Image of Logistic Regression Batch Predictions

BigML batch predictions allow you to predict multiple instances with one-click. Just select the logistic regression and the dataset containing the data you want to predict, and BigML will automatically generate an output CSV file with a prediction for each of your instances.

You can also configure a wide range of the output file settings, e.g. you can include all the objective field classes probabilities for each of the instances in your dataset.

batchpredictions logisticregression classification supervised dashboard summer2016
WhizzML: Automating Machine Learning
May2016
Image of WhizzML: Automating Machine Learning

BigML is proud to announce WhizzML, a new domain-specific language for automating Machine Learning workflows and implementing high-level algorithms.

WhizzML abstracts away the complexity of the underlying infrastructure and offers out-of-the-box scalability. With WhizzML you can easily transform time-consuming repetitive tasks into 1-click actions or into a single API call. WhizzML provides a standardized way to implement high-level Machine Learning algorithms on your own, e.g. Gradient Boosting or Stacked Generalization.

You can also clone many advanced workflows and algorithms from WhizzML Gallery and share yours with others!

api dashboard scripts libraries executions automation workflows algorithms whizzml spring2016
Batch Importance Scores
Mar2016
Image of Batch Importance Scores

This feature enables you to include a set of percentages indicating how much each field in your dataset contributed to a given anomaly score when creating a Batch Anomaly Score. You can include those values in your output file either with BigML Dashboard or the API. This will give you a better understanding of your anomalous instances as it will reveal which factors are causing them to be seen as anomalous.

anomaly detector batch anomaly scores importance scores api dashboard anomalyscore winter2016
Associations datasets
Feb2016
Image of Associations datasets

BigML associations let you discover meaningful relationships among dataset fields and their values. Now you can easily select the rules that you want from the list of associations found by BigML and create a filtered dataset from those. This allows you to conduct further analysis on the filtered dataset instances matching those association rules.

datasets filter items winter2016 association dashboard
Export datasets to Tableau
Jan2016
Image of Export datasets to Tableau

Many of you are already benefiting from the ability to incorporate and visualize your BigML models within Tableau. Now you can also export your datasets from BigML in .tde format with just 1-click. This enables you to visualize any BigML dataset (e.g., batch predictions, batch centroids, batch anomaly scores) within Tableau.

dataset dashboard export tableau winter2016
Hadoop Integration
Jan2016
Image of Hadoop Integration

We are always on the lookout for new ways to help you use your remote data sources. With our new Hadoop integration you can upload new data to BigML directly from a Hadoop server by using a remote URL starting with "hdfs://", either from our Dashboard or our API.

hadoop remote data dashboard api miscellaneous winter2016 source
Association Discovery
Dec2015
Image of Association Discovery

BigML team has worked really hard to launch Association Discovery this Fall 2015. We are proud to be the first cloud-based platform that offers this unsupervised Machine Learning method to find meaningful relationships between values in high-dimensional datasets. BigML acquired Magnum Opus from professor Geoff Web (Monash University, Melbourne) combining the best-in-class Association Discovery technology with BigML easy-to-use platform.

web unsupervised machine learning algorithm fall2015 association market basket analysis
Partial Dependence Plots
Dec2015
Image of Partial Dependence Plots

Ensembles are one of the top performing algorithms for most Machine Learning problems, but they are also hard to interpret. Partial Dependence Plot (PDP) is a graphical representation of the ensamble that allows you to visualize the impact that a set of fields have on predictions. BigML provides a configurable two-way PDP where you can select the fields for both axis to analyze how they influence predictions. PDP can be used for regression and classification ensembles.

ensembles predictions visualization viz web labs fall2015 ensemble
Logistic Regression
Oct2015
Image of Logistic Regression

Logistic Regression is a supervised ML model to solve classification problems and it's now available in the API and BigMLer. It can be expressed according to the following formula:

y = 1 / {1 + e^[-logit(p)]}

where logit(p) = b_ 0 + b_ 1 * x_ 1 + ... + b_ k*x_ k

Each of the independent variables (x1, x2... xK) are the predictors of the model. Logistic regression seeks to learn the coefficient values (b0, b1, b2, ... bk) from the training data using non-linear optimization techniques and returns a probability for each of the predicted classes (y).

api supervised algorithm classification BigMLer fall2015 logisticregression
Statistical Tests
Oct2015
Image of Statistical Tests

Use statistical techniques to explore your dataset fields. Common usages:

  • Fraud detection: by relying on Benford’s Law you can find symptoms of anomalous values in your dataset fields

  • Normality: find out whether the data in a field is normally distributed. Tests: Anderson-Darling, Jarque-Bera, Z-score.

  • Outliers: find out whether a field contains any value that differs significantly from the mean. Tests: Grubbs.

api dataset statistics fall2015 statisticaltest
Flatliner editor in your dashboard
Oct2015
Image of Flatliner editor in your dashboard

The Flatliner code editor is now available from the dataset configuration menu. You can use it to add more fields or to filter your dataset.

web dataset fall2015
Correlations
Sep2015
Image of Correlations

Find correlations between your dataset fields with this option available in the API. You just have to select a dataset and you will get some measures to detect the correlations between each of your dataset fields and the objective field. Correlations measures available:

  • Numeric-numeric fields: Pearson and Spearman coefficients

  • Numeric-categorical fields: one-way ANOVA (Eta-square, F-ratio)

  • Categorical - categorical fields: Contingency table, Chi-square, Cramer, Tschuprow

dataset api correlations fall2015 correlation
Download datasets bought in the Gallery
Jun2015
Image of Download datasets bought in the Gallery

Free datasets "purchased" in the BigML Gallery can be now downloaded as CSV.

api web gallery dataset
Move resources between projects
Jun2015
Image of Move resources between projects

Now users can better organize their resources by moving them from one project to another. Sources can also be moved from production mode to development mode and the other way around.

ui api project source dataset model ensemble evaluation cluster anoamly detector centroid anomaly score prediction web
New view: Projects
May2015
Image of New view: Projects

New view for Projects with built in search. Get a summary view of your projects in a single view.

project web ui
Flatliner code editor & evaluator
Apr2015
Image of Flatliner code editor & evaluator

Flatline is BigML’s Lisp-like language that enables you to programmatically perform a vast array of data transformations, including filtering and new field generation. Our newest BigML Labs project Flatliner is a handy code editor that helps you visually test your Flatline expressions before you use them.

dataset labs filter transform flatline sample miscellaneous
Evaluation Comparison
Apr2015
Image of Evaluation Comparison

You can now compare multiple evaluations against a test set in a ROC space. The graph can then be downloaded as a .PNG image, and the performance measures can be exported as a .csv for further analyses.

comparison auc evaluation labs
Google Integration
Jan2015
Image of Google Integration

With the Winter Release, you'll now be able to add sources to BigML through Google Cloud Storage and Google Drive, similar to our prior integrations with Dropbox and Azure Data Marketplace. You can also now log into BigML using your Google ID.

google datasources google drive google cloud storage winter2015 web
Projects
Jan2015
Image of Projects

We're happy to introduce Projects to help you organize your machine learning resources. You only have to create a new project using the web interface or the API resource and update a new source to this project. All the new resources created from this source will be associated to the same project.

winter2015 projects miscellaneous
Dataset Comparison
Dec2014
Image of Dataset Comparison

This is another simple but useful application we have released into our new BigML Labs. It allows users to compare side by side two different datasets. Check it out here.

dataset winter2015 labs web
Sample Service
Dec2014
Image of Sample Service

BigML's new Sample Service provides fast access to datasets that are kept in an in-memory cache which enables a variety of sampling, filtering and correlation techniques. We have leveraged this new service to create a Dynamic Scatterplot visualization that we've released into BigML Labs.

sample dataset viz visualization winter2015 labs api
BigML Labs
Dec2014
Image of BigML Labs

Our team is constantly working on innovative applications built on top of BigML's API. We're now unveiling several of these in early access through our BigML Labs.

labs winter2015 miscellaneous
G-means Clusters
Dec2014
Image of G-means Clusters

This latest addition to BigML's unsupervised learning algorithms is ideal for when you may not know how many clusters you wish to build from your dataset.

gmeans winter2015 cluster
Cluster summary report
Oct2014
Image of Cluster summary report

Now you can download a Summary Report for your BigML Clusters. This report will inform you on the distribution of data across your clusters, as well as the associated features and data distances.

report cluster
Anomaly Detector
Sep2014
Image of Anomaly Detector

BigML makes it easy to build a top-performing anomaly detector that will help you identify instances in your dataset that do not conform to a regular pattern.

fraud detection summer2014 anomaly
Batch Anomaly Scores
Sep2014
Image of Batch Anomaly Scores

You can quickly score multiple lines of data through BigML's Batch Anomaly Score. The output can be downloaded as a .csv and/or you can use it to automatically create a new dataset.

batches fraud detection anomalyscore summer2014
Anomaly Score
Sep2014
Image of Anomaly Score

You can score individual data points against your anomaly detector by using the web interface. Simply input the variables and BigML will provide you with an anomaly percentage (a higher score reflects greater anomaly).

score fraud detection anomalyscore summer2014
New dataset from batch prediction output
Sep2014
Image of New dataset from batch prediction output

Batch predictions are a powerful way to score likely outcomes on multiple rows of data. You can now create a new dataset directly from the batch prediction output (in addition to getting the output as a .csv file).

batch prediction batch centroid batch anomalyscore workflow summer2014 dataset
Models from clusters
Aug2014
Image of Models from clusters

Now you can automatically create a model for each cluster that will not only help you better understand the cluster, but also use it to classify new instances.

model summer2014 cluster
Modeling with missing splits
Aug2014
Image of Modeling with missing splits

As we know that cleaning up data might be hard and having all the input data handy at prediction time is important, we have built a new option to create models that will generate predicates that explicitly deal with missing values.

missing values ensembles summer2014 model
Online predictions
Jul2014
Image of Online predictions

New client-side predictions make it easier than ever to explore the influence of each field in your models, ensembles or clusters. In addition, we are open sourcing the related Javascript libraries so you can leverage this functionality to build very powerful and dynamic apps and web services.

free client-side javascript summer2014 prediction
Fast ensembles
Jul2014
Image of Fast ensembles

We have refined the way the models of an ensemble are built to save a great amount of time in data transportation. This will dramatically speed up creation of your ensembles.

fast summer2014 ensemble
Dropbox: new data source
Jun2014
Image of Dropbox: new data source

In another feature that we've created based on user demand, you can now use your Dropbox storage to bring new datasets to be analyzed in BigML. To activate this feature you have to visit the Cloud Storages section in your BigML account settings, and then allow BigML to access your Dropbox files. Note that BigML only reads your files for the purpose of downloading them into your Dashboard, and you can revoke the grant at any time in your account settings.

Once you've granted BigML access to your Dropbox account, you can browse your Dropbox account within BigML to identify sources that you’d like to download.

dropbox import remote source
Field Importance Histograms
Jun2014
Image of Field Importance Histograms

Based on user feedback, we've created a new Field Importance histogram that helps visualize these insights from the text in the Model/Ensemble Summary Report. You can access this new report for both your models and ensembles.

visualization histogram report model ensemble web
BigML Clustering with Java
May2014
Image of BigML Clustering with Java

The Java BigML bindings have been updated with support for the new clustering analysis. Create new clusters, predict centroids and batch centroids using our REST API and Java. Clone or fork it from this GitHub repo.

api cluster centroid java bindings
Python Bindings with Clustering support
May2014
Image of Python Bindings with Clustering support

Do clustering analysis in python with the new version of the BigML Python bindings. We have added support for managing clusters, centroids, and batch centroids. Clone or fork them from GitHub.

python clusters centroids api REST bindings
Cluster Analysis
May2014
Image of Cluster Analysis

BigML's first unsupervied learning offering enables users to group the most similar instances from your dataset into Clusters. BigML's approach to Clustering is inspired by k-means and features the intuitive workflow and rich visualizations that you've come to expect from our service. Read more on this feature in our blog post.

unsupervised learning clustering model
Cluster centroids
May2014
Image of Cluster centroids

Using a cluster you can predict the closest centroid for a new instance of data.

clustering clusters prediction centroid
Batch centroids
May2014
Image of Batch centroids

As we already do with batch predictions on models and ensembles, you can also compute centroids in batches using an existing cluster and a dataset. Predict the closest centroid of each instance of the selected dataset.

batch multi-preidctions dataset prediction centroid
Dataset exports
Mar2014
Image of Dataset exports

Now you can also export datasets from a dataset view into a comma-separated values (.CSV) file. This works very well in combination with the dataset creation from a model segment as it can help you identify the instances that follow certain criteria.

export download web
Segment-based datasets
Mar2014
Image of Segment-based datasets

Have you ever wanted to create a new dataset for further analysis from a specific node in a tree? Now you can! When you're in a model or sunburst view, simply mouse over a node and then press your keyboard's shift button. This will freeze the view and allow you to export the rules for that segment and/or create a new dataset with the instances at that node.

model dataset filter flatline web
Segment Actionable Models
Mar2014
Image of Segment Actionable Models

Download the actionable code of the rules defined by a segment of your predictive model.

model actionable model web
Open SunBurst
Jan2014
Image of Open SunBurst

BigML's SunBurst visualization for decision trees is an intuitive, interactive way for users to experience data. Now you can include a fully interactive SunBurst viz in any web page simply by copying and pasting a snippet of HTML. Great for blog posts and news articles!

Read more about this feature in this blog post.

sunburst model decision tree secret link embed viz visualization web
Add new fields to your dataset
Jan2014
Image of Add new fields to your dataset

You can now add new fields to your dataset computed from existing features. There is a set of predefined generators and you can also define your own using our flatline expression language. This features is also available through the API.

web api extended flatline dataset
K threshold
Jan2014
Image of K threshold

There is a new way of combining predictions from models within an ensemble called k-threshold. With this combiner you can control the trade off between the precision and recall of your predictions and tune the risks you take when making predictions.

ensemble web api prediction
DEVELOPMENT mode
Jan2014
Image of DEVELOPMENT mode

Why should free trials be limited to one month? BigML’s new development mode allows you to run unlimited tasks of up to 16 MB for FREE, FOREVER, making BigML the ideal framework to practice, teach, and learn machine learning or predictive analytics.

BigML’s development mode has 3 limitations compared to production mode:

  • The maximum number of models of an ensemble cannot be higher than 10.

  • The maximum number of terms in text analysis is limited to 32.

  • The maximum number of nodes in a tree cannot be higher than 512.

All other features are exactly the same as our production mode. You can run unlimited tasks and up to 4 tasks in parallel.

Remember to prefix your URLs with "dev/" to get access from BigML's API.

api dev development free web
Search resources by name
Jan2014
Image of Search resources by name

Filter your resources by name makes easier to navigate your BigML dashboard.

search filter sources datasets models ensembles predictions evaluations web
Sample datasets
Jan2014
Image of Sample datasets

Have you ever wanted to create a new dataset from a sample of your original dataset? Now you can using different sample rates, different ranges of instances, choosing between random or deterministic samples, using replacement or not, or using out-of-the-bag samples.

sampling flatline dataset api web
Filter datasets
Jan2014
Image of Filter datasets

Have you ever wanted to create a new dataset to model a specific segment of your data? Now BigML comes with a simple but powerful way to create new datasets using combinations of filters on several fields of your dataset. This feature is even more powerful through the BigML API.

filters flatline dataset api web
Node Threshold in predictive models
Jan2014
Image of Node Threshold in predictive models

Increase the maximum number of nodes in your trees to boost their predictive power and improve the accuracy and confidence of their output.

node threshold tree model
Predictions with Missing Strategy
Jan2014
Image of Predictions with Missing Strategy

When making predictions with partial data you can now choose wether the algorithm should take into account unexplored tree branches to compute the final prediction (proportional strategy) or just stop at the given node (last prediction strategy).

web api strategy prediction
Faster predictive models with MTree
Jan2014
Image of Faster predictive models with MTree

Our new algorithm has significantly improved our performance when it comes to model building. Now you can build a model in 1/8 of the time it previously took.

mtree model
Secret Links for Evaluations
Jan2014
Image of Secret Links for Evaluations

You can now share evaluations with co-workers or customers using secret links. Visit the evaluation that you want to share, click on the more info icon, open the privacy panel, and switch the secret link button. Anyone with the secret link will be able to access the evaluation.

secret links sharing evaluation web
Transformations
Jan2014
Image of Transformations

Need even more ways to transform your data? Now you can derive a new dataset by sampling, filtering, and even extending it with new fields, or concatenating it to other datasets.

In fact, you can sample, filter and extend a dataset all at once with only one API request.

flatline programatic machine learning dataset api
Flatline: Programatic Machine Learning
Jan2014
Image of Flatline: Programatic Machine Learning

A new Lisp-like language named Flatline allows you to not only filter the rows and columns of a dataset but also generate new fields.

With Flatline you can select different fields in the same row of a dataset or select a finite sliding window of rows to traverse a dataset vertically and apply functions to them. This is useful to generate values based on a number of front and rear values.

If you prefer you can use its JSON-like variant.

flatline programatic machine learning dataset api
Weights
Jan2014
Image of Weights

BigML’s latest release comes with three ways to elegantly cope with imbalanced datasets and create weighted models. Using them you’ll be able to build models that will consider at building time every instance or class according to the weight criteria that you establish. Read more in our developers documentation

weights model dataset api
Multi Datasets
Jan2014
Image of Multi Datasets

BigML's API allows you to create a dataset using multiple datasets as input. This is very useful when you need to combine multiple sources of data into a single dataset or when you want to build an online solution that collects data in batches.

You can also sample each dataset individually.

multidataset api dataset
Batch Predictions
Nov2013
Image of Batch Predictions

A long-awaited feature is finally here!!! BigML now allows you to create batch predictions for thousands or millions of data points without writing a single line of code. Just upload the data you want to create predictions for, transform it into a dataset and use it together with the model or ensemble to generate a downloadable file with all the predictions. You can give the file multiple formats.

There's also a new BigML.io resource that you can use to programmatically create batch predictions.

batch predictions web API prediction
Secret Links for Datasets
Oct2013
Image of Secret Links for Datasets

From now on, BigML datasets can be shared through private links analogous to those already available for models.

secret links sharing dataset web
Text Analysis
Sep2013
Image of Text Analysis

Have you ever wanted to create predictive models using a mix of structured and unstructured data but weren't able to find a package or service available to do so? BigML now allows you to process multiple text fields, alongside numerical, categorical, date and time fields. BigML has implemented a number of basic Natural Language Processing techniques to spot relationships between text content and other properties of your data. For example, wouldn't it be good to know what keywords from your social media feed are resulting in the most social media shares? This is now possible through BigML.

text analysis text fields web api
Multi-label Classification
Sep2013
Image of Multi-label Classification

Sometimes you need to assign multiple classes (labels) to your data. For example, what subjects a student will enroll next year? Or, what keywords best describe a text? BigMLer, our command-line tool for Machine Learning, makes multi-label classification very easy: in just one line you can generate a combination of models that will help you predict all the classes to which a new instance belongs.

bigmler multi-label classification
BigML PredictServer
Sep2013
Image of BigML PredictServer

A dedicated server available from Amazon Web Services that lets you run lightning fast predictions against a model or ensemble you created in BigML. Available today in early access form, BigML PredictServer is a great solution for customers that need predictions in real-time or in large batches.

predictserver real-time prediction API
Microsoft Excel ® Export
Sep2013
Image of Microsoft Excel ® Export

Microsoft Excel is one of the most pervasive “analytics” tools on the market today. Now you can export your BigML models and make them actionable on Excel—letting anyone in your organization make predictions on the go and analyze BigML models from the comfort of their own tools and environment.

Excel model prediction web
Confusion Matrix
Sep2013
Image of Confusion Matrix

A highly-requested enhancement to BigML’s Evaluations, BigML’s intuitive confusion matrix makes it easy for you to visualize the performance of your classification models and ensembles by quickly showing you the actual vs. predicted results highlighting false negatives and false positives. Also exportable to Microsoft Excel.

evaluation classification web
Secret Links
Sep2013
Image of Secret Links

Have you ever wanted to share a model with a colleague, but not post it in BigML's Gallery? Now you can through a simple copy & paste! As always, your data is completely safe with us—the link provides access to the model, and nothing else.

secret links sharing model web
Inline Field Editing
Sep2013
Image of Inline Field Editing

Add labels and descriptions to fields in your sources and datasets that will carry over to your models and predictions—this is great for making your data easier to understand and analyze.

labels descriptions source dataset web
Sending Request...
Sending Request...