Verticals

Time series are eating the data world: most industrial processes are already time-dependent,and the current proliferation of connected sensors will only compound the need for proper time series modeling.

shutterstock_768607153

Logistics

Logistics is ideal for modern time series modeling: time series are everywhere, and the time constraint is severe. The proliferation of sensors on trucks, cars and containers will only compound the problem. Datapred applications in logistics - by freight forwarders or the logistics teams of industrial groups - include:
  • Demand prediction
  • Dynamic inventory allocation
  • Transport order prioritization
  • Delivery delay prediction

Industrial optimization

Batch machine learning for predictive maintenance rarely makes good on its promises - ratios of 20 false positives to 1 true positive are common. Correctly integrating the time dimension of your industrial optimization challenge with Datapred will increase accuracy for:

  • Performance monitoring and prediction
  • Anomaly detection
  • Failure prediction
  • Risk factor identification
shutterstock_1062476168

shutterstock_1011952036

Procurement & Finance

Sequential machine learning was invented for financial markets. Datapred gives finance and procurement professionals the best sequential learning framework on the market and the ability to integrate custom - and potentially complex - cost functions. It’s an unbeatable combination for:
  • Raw material price prediction
  • Purchasing program optimization
  • Risk scoring
  • Risk factor identification

Marketing

Ten years ago, customer satisfaction was measured by monthly surveys. Today, it is quantified in real time by bots scraping the internet for natural-language comments. This is one of many examples of how much time-dependent marketing has become. Our marketing clients use Datapred for:
  • Churn prediction
  • Churn factor identification
  • Client satisfaction modeling
shutterstock_503419588

shutterstock_531875605

…and more

Datapred will outperform whenever the time factor is key and the challenge is too complex for traditional statistics. If such is your case, give Explore a try or contact us to discuss how Install or Embed could help.


Datapred is a comprehensive machine learning suite for time series

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.

Connectors

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.


shutterstock_241475083_1920-compressor

What is your time series modeling challenge?

Start experimenting with Datapred Explore, or discuss how Datapred Install or Datapred Embed could help.

Start with Datapred Explore
Discuss Install or Embed

Features

  • 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