Machine learning for time series

Key concepts and useful resources.


Time series is sequentially revealed, time-stamped and time-critical data.

Just like "software is eating the world", time series are eating static data sets.

  • The proliferation of time-stamped data follows naturally from the digitization of industry. The ongoing deployment of billions of connected sensors will only accelerate the trend.
  • As a consequence, lots of decision-making processes that used to be fairly static (based on stable information) are becoming dynamic (based on streaming data).
The problem for data scientists is that time series modeling differs significantly from standard machine learning practices. (For excellent overviews of these differences, click here and here.)

The problem for operational managers is that standard machine learning solutions applied to time series underperform.


This page provides short explanations and links to interesting resources about the three main aspects of machine learning for time series: preprocessing, modeling and post-processing.



You don't need perfect data streaming from a brand-new data lake to build valuable machine learning solution for time series. But you do need to handle your data carefully.

The resources below deal with the preprocessing steps required for efficient time series modeling.


Modeling is the core of the data scientist's jobs. The possibilities are endless, and the state of the art fast-moving.

Surprisingly given how pervasive time series are, the specificities of time series modeling are not well known. The resources below cover the main aspects of time series modeling.


Congratulations, your machine learning prototype is ready. Does it mean it is ready for production? Unfortunately not... Pre-processing and modeling are only half of the job. Software packaging (« post-processing ») is the other half - technical, fastidious, but absolutely necessary.

The resources below describe the main post-processing tasks required for machine learning and time series.

Datapred is a powerful modeling engine for continuous intelligence.

Data sequentialization

Your time series in the right order, whatever their frequency.

Stationarization and filtering

Extract meaningful features in your data, sequentially. Spot and handle outliers automatically.

Built-in models

Hit the ground running with our diverse portfolio of built-in predictive models.

Compatibility with ML libraries

For advanced custom modeling, Datapred is compatible with most open-source machine learning libraries.

Aggregation and stacking

Forget selecting the best model: boost performance and versatility by using multiple models at the same time.

Custom cost functions

Optimize for the right objective, under realistic constraints.

Parallelization and distribution

Parallel architecture that optimizes computations at every modeling step.


Pre-built connectors for standard databases, and templates for connecting to non-standard databases and proprietary management systems.

Graph structure

Leverage Datapred’s graph structure to build consistent, flexible and robust machine learning workflows.

Performance monitoring

Rigorous, online and customizable measurement of your solution’s performance.

Checkpoints and backups

Automatic backups at each time step, in your chosen format, for final or intermediate results.

Continual improvement

Create a sandbox and continually test the contribution of new data sources and modeling options to your original solution.


What is your continuous intelligence challenge?

Contact us or download our datasheet to understand how Datapred could help with your continuous intelligence projects.


Contact us    Download datasheet


  • Data sequentialization
  • Stationarization and filtering
  • Built-in models
  • Compatibility with ML libraries
  • Aggregation and stacking
  • Custom cost functions
  • Parallelization and distribution
  • Connectors
  • Graph structure
  • Performance monitoring
  • Checkpoints and backups
  • Continual improvement