Skip to content

Latest commit

 

History

History
44 lines (33 loc) · 2.69 KB

README.md

File metadata and controls

44 lines (33 loc) · 2.69 KB

MULTIFOR: A Multidisciplinary Framework for the identification of new target markets by open time-series data and deep learning methods

MULTIFOR framework abstract view
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

MULTIFOR framework abstract view
Fig.2 - MULTIFOR Web Service

The MULTIFOR Web app, as demonstrated in Figure’s 3 site-map, consists of the three following pages:

MULTIFOR site-map
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.
map_page
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.
    pestel_page
    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.
    chart_page
    Fig.6 - Chart page