You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
MULTIFOR: A Multidisciplinary Framework for the identification of new target markets by open time-series data and deep learning methods
Fig.1 - MULTIFOR framework abstract view
Framework
MULTIFOR framework principles, are the following:
Robust PESTEL analysis, as a means of selecting the
appropriate indicators (features) that are necessary to carry
out the Business Internationalization,
A set of predefined indicators for European countries
Open data exploitation.
Implementation of a LSTM RNN approach,
Non-stationary time-series forecasting.
The MULTIFOR Web service architecture
Fig.2 - MULTIFOR Web Service
The MULTIFOR Web app, as demonstrated in Figure’s 3 site-map, consists of the three following pages:
Fig.3 - Site-map
Map Page, which is the home page, and contains an interactive map of the European countries included in the project, as illustrated in the screenshot of Figure 4.
Fig.4 - Map page
PESTEL Analysis page, which contains an interactive pie chart with the PESTEL analysis headers, revealing their included indicators in a list whenever hovered, as displayed in Figure 5.
Fig.5 - PESTEL-Analysis page
Charts Page, a screenshot of which is depicted in Figure 6, contains the main functionality, developed for the main interaction with the user for time-series analysis, compare and forecasting.