EPOCH – Event Prediction from Hybrid Datasets

Project Start: 01 January 2019
Consortium: MODUL Technology, webLyzard technology, Ketchum Publico, KPMG
Funding: Federal Ministry for Transport, Innovation and Technology (bmvit), ICT of the Future Program

EPOCH will measure the effects on statistical indicators of events being reported in the news and social media. Innovatively, it will use the measured effects of now past events to predict the future changes expected due to future events detected in the public dialogue. Through the EPOCH dashboard, organizations can identify and thus better prepare for these changes, adapting their communications, marketing and resources accordingly. This will be demonstrated in the domains of purchase price forecasting and public relations.

Motivation

Any organization today, in any domain, has to plan for the future without having full knowledge of what the future will bring. Appropriate planning is vital to corporate success, whether in making the right operational decisions (ensuring higher stock levels in times of expected rising prices, minimizing stock in times of expected falling prices), maximizing the success of marketing campaigns or getting the message and timing right in internal and external communications. While we may never know everything that the future will bring, a lot of planned and expected future events are referenced every day in the news and social media.

Goals and Use Case

EPOCH will advance the state of the art in event detection and predictive analytics, combining both methods in an innovative manner in order to predict the impact of future events based on observed patterns regarding past events. The result will be the EPOCH platform and dashboard, prototyped for the purchase price forecasting and public relations domains, which can provide stakeholders with far greater insight into future developments in their domain than available today.

Analytic Methods

Quantitative evaluations will assess the predictive capabilities of this dashboard, intended to complement existing time series data and extrapolation-based tools, while qualitative evaluations will prove its usability for our use case partners Ketchum Publico and the KPMG Austria.