future

Forecasting was never so simple.

Forecast quality suffers because everything else is complicated enough?

Spent days working on your data, only to have time left for standard methods to generate forecasts? Now, you can get great forecast quality automatically and with minimal effort.

Forecasting — done.

No need to worry about detailed settings that require deep research, special cases, scalability, or plausibility checks. With futureEXPERT, you get 100 years of forecasting experience built in.

Easily integrated into your Python code.

Avoid having you and your colleagues get used to yet another platform. Integrate the SaaS solution futureEXPERT directly into your system - from quick prototypes to production-ready software.

Features of future

You can decide for yourself how many automated features to use and which settings to configure on your own with complete flexibility.

In the future modules, you’ll find many helpful features bundled together. Click the buttons to learn more!

Forecast methods

30+ methods in statistics and machine learning

Model selection

Various forecast methods are automatically ranked and selected

Covariates

Identify relationships with your influencing factors, detect lags, and use them in the forecast

Database

with a selection of influencing factors, such as economic indicators, weather, prices

Granularities

For annual, quarterly, monthly, weekly, daily, hourly, and half-hourly time series

Data preparation

of time series conducted with ease via the frontend or code

Seasonalities

can be automatically detected or set by you, including multiple seasonalities

Outliers

can be identified and replaced with plausible values

Prediction intervals

at any prediction confidence level alongside point forecasts

Backtesting

to evaluate historical forecast performance for desired iterations and forecast steps

Forecast horizon

can be chosen flexibly, with the forecast optimized accordingly

Accuracy measures

various different accuracy measures (MSE, MAPE, MASE, PIS, …)

Time series classification

Detection of smooth, erratic, or sporadic patterns

Fallback mechanisms

A sensible alternative if models fail or data history is too short for backtesting

Plausibility checks

Implausible forecasts are intercepted, inappropriate values in the raw data detected

Global settings

such as upper & lower limits and rounding to integers

Change points

like level shifts and structural breaks are detected

Quantized values

are automatically recognized and considered in the forecast: package sizes, ordering behavior, …

SaaS platform

ensures quick result delivery in the background through automatic scaling

Visualization

of data and results in the interactive frontend of futureNOW or through Python plots via futureEXPERT

Just try out the features for free!

future in use

Only by putting futureEXPERT into action can it show its full power. Let our customers’ applications inspire you.

Demand Planning

Bildschirmaufnahme des Use-Case Bildschirmaufnahme des Use-Case Bildschirmaufnahme des Use-Case Bildschirmaufnahme des Use-Case
  • Negative sales and forecasts automatically intercepted

  • Structural breaks detected, and package sizes included in forecasts

  • High forecast accuracy ensures acceptance by planners

  • Planners work with the results in the familiar dashboard

  • Results are fed directly into the ERP system via suitable interfaces

Sales Forecasting

Bildschirmaufnahme des Use-Case Bildschirmaufnahme des Use-Case Bildschirmaufnahme des Use-Case Bildschirmaufnahme des Use-Case
  • Regional revenue forecasts with point estimates and prediction intervals

  • Clustering of economic indicators provides an overview of the market environment

  • Time-shifted indicators analyzed for each region’s sales

  • Trend changes detected early and considered in the forecast

  • Always up-to-date results serve as an objective foundation for strategic decisions.

Scenario Forecasts for Prices

Bildschirmaufnahme des Use-Case Bildschirmaufnahme des Use-Case Bildschirmaufnahme des Use-Case Bildschirmaufnahme des Use-Case
  • Incorporates both custom influencing factors and those available in POOL

  • Relevant influencing factors with their lags identified using MATCHER

  • Fully automated worst- and best-case scenarios generated

  • Scenario forecasts enhance transparency in dynamic market environments.

  • Experts transfer their knowledge from one market to another using the system.

  • Custom visualization tool enables ‘what-if’ analyses anytime.

FAQ

What makes futureEXPERT different from other forecasting solutions?

futureEXPERT is built on many years of project experience from diverse customer use cases, especially in demand planning, sales forecasting, and energy requirements. The recurring challenges in many projects, which often required additional effort, special-case handling, or even manual review, have been gradually automated over the years — resulting in a refined "data scientist's eye."

futureEXPERT combines methodological expertise with practical experience, offering a user-friendly way to tailor solutions to use cases. On the one hand, you can get results quickly and easily thanks to the highly automated pipeline; on the other, you can manually intervene and get results from various methods (ranked and selected).

If you have any questions, suggestions, or requests, feel free to reach out to us, and we’ll do our best to meet your requirements.

What's the easiest way to get started with futureEXPERT ? And where can I find more information?

After registering, the easiest way to get started is with this Jupyter Notebook . If something doesn’t work right away, you'll find additional useful tips for getting started in the README. For more in-depth information, you can check out the API Docs and the manual in the frontend , or refer directly to the help texts in the relevant areas of the frontend. Additionally, you have access to more notebooks with specific application examples .

What data formats are supported?

Both futureNOW and futureEXPERT support raw data in CSV or TSV format with UTF-8 encoding. In addition, futureEXPERT also supports data formatted in the widely-used pandas DataFrame format.

What happens to my data when I upload it?

Your data is stored and encrypted on servers located entirely in Germany and is not shared with anyone else. Our hosting partner is ISO 27001 certified.

But I need it in a programming language other than Python, is that possible?

futureEXPERT is available as a Python client. You can also directly access our API from another programming language and use our convenient forecasting features wherever you need them. Feel free to reach out to us if you need assistance.

Where do I turn for issues or questions?

Your first point of contact for questions or issues related to using futureEXPERT is the futureEXPERT GitHub repo . You can also submit any ideas or feature requests there. We constantly monitor this and will respond to your issue as quickly as possible. If you have questions about subscription packages or further requirements not included in the subscription, feel free to contact us at +49 931 497386-30 or support@future-forecasting.de.

What is the minimum contract period?

There is no minimum contract period or cancellation notice period! You can choose between a monthly or annual subscription. After the end of the month or year, your selected subscription package will automatically renew for another month or year.

How can I switch my package or perform an upgrade?

As a registered user, you can switch your subscription package in your booking information . If it's an upgrade (to a higher package or switching to annual payment), the change will take effect immediately. In other cases (switching to a lower package or monthly payment), the change will take effect after the current month/year ends.

What if I have very specific requirements?

futureEXPERT is a ready-to-use standard solution that can be tailored and configured to the specific needs of all customers and industries. Feel free to contact us at +49 931 497386-30 if you need further consultation or would like to discuss custom adjustments.

For which companies and industries is futureEXPERT relevant?

futureEXPERT is the right solution for companies that value future-oriented business models and use data to manage and optimize their business processes. This includes sales planning, demand forecasting, production, inventory planning, purchasing, or logistics optimization. futureEXPERT is used by companies of all sizes across various industries, such as retail, logistics, production, and the energy sector...

Benefit directly from good forecasts.

Using futureEXPERT, you can swiftly create prototypes and build productive solutions. Get started in just a few steps.

  1. Create your account now.
  2. An interactive notebook guides you through the application - just customize it to fit your needs! Test data is available from the get-go.
  3. It's time to bring your idea to life! Start with your own data to create your solution.
Account, tests in notebooks, create your application
You are about to leave our website via an external link. Please note that the content of the linked page is beyond our control.

Cookies und andere (Dritt-)Dienste

Diese Website speichert Cookies auf Ihrem Computer nur, wenn Sie dem ausdrücklich zustimmen. Bei Zustimmung werden insbesondere auch Dritt-Dienste eingebunden, die zusätzliche Funktionalitäten, wie beispielsweise die Buchung von Terminen, bereitstellen. Diese Cookies und Dienste werden verwendet, um Informationen darüber zu sammeln, wie Sie mit unserer Website interagieren, und um Ihre Browser-Erfahrung zu verbessern und anzupassen. Zudem nutzen wir diese Informationen für Analysen und Messungen zu unseren Besuchern auf dieser Website und anderen Medien. Weitere Informationen zu den von uns verwendeten Cookies und Dritt-Diensten finden Sie in unseren Datenschutzbestimmungen.