Truly refreshing document digitalisation Unlock the full potential of your documents using machine learning

Project Information

MINT.extract

Grant agreement ID: 854135

DOI

10.3030/854135

Project closed

EC signature date 30 January 2019

Start date 1 February 2019

End date 31 May 2019

Funded under

• INDUSTRIAL LEADERSHIP - Innovation In SMEs

Total cost

€ 71 429,00

EU contribution

€ 50 000,00

Coordinated by

TURICODE AG
Switzerland

Periodic Reporting for period 1 - MINT.extract (Truly refreshing document digitalisation Unlock the full potential of your documents using machine learning)

Reporting period: 2019-02-01 to 2019-05-31

Summary of the context and overall objectives of the project

Vast majority (80%+) of data existing is unstructured. The Financial Services Industry is extracting information from different unstructured documents manually which is very repetitive, time-consuming and error-prone.
The importance lays in the fact that companies can re-direct their most valuable resources, employees, to tasks that require human understanding and decision making.
The objective of the project is to develop a generic learning system to be applied to a diverse set of document types used in Financial Services Industry delivering fully automated results with a superior quality

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

Technical feasibility – defined a technological roadmap to reach TRL9 by defining work packages with objectives, timeline, cost and risks.
Commercial roadmap – we carried out a deep market study into Financial Services Industry, re-defined target subscription plans and market introduction strategy as well as countries to enter and Serviceable Obtainable Market (SOM) and commercialization risks.
Partnering – we have already signed several Channel Partners, evaluated the risks and entered further negotiations.
Freedom-to-Operate: we have carried out an FTO and the result is that we have freedom to operate. We also mapped our intellectual assets and updated IPR strategy. We analyzed relevant regulations: to be implemented by turicode or that affect our customers and therefore their document types and data requirements.
Financials – we refined our financial plan depending on market study, SOM and technical budget need.
We have concluded all the above in a business plan.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

Our project opens the door to extract value from documents automatically, by using supervised and unsupervised Machine Learning with text-based and pixel-based methods. This allows us to provide services with unmatched output quality and create significant speed-up in the process of information extraction in a broad field of application within Financial Services Industry.
We started collaboration with an insurance industry association giving us the opportunity to become a certified technology provider, as well as get access to industry knowledge and training sets of data. The impact on turicode in 3 years after the start of commercialization is 26-fold increase in revenue and about 5-fold growth in team size.
Societal implication of MINT.extract the higher job satisfaction in the Financial services Industry due the elimination of boring manual tasks allowing employees to concentrate on more challenging work.

image-1.png