Omen
Omen is a fully customizable web-based FSS with a modern and efficient interface which uses exclusively open-source solutions and supports state-of-the-art methods and models. Through OMEN we demonstrate the limitations of typical off-the-shelf solutions and explain how some of its feautures could be used to improve modern FSSs. As presented, typical off-the-shelf solutions are windows-based applications which limit the availability, the accessibility and the compatibility of the system, while increasing their complexity and the use of resources. Moreover, given their architecture and structure, FSSs are difficult to be customized leading to inflexible and generic software which are not targeted to the special needs of each company and can therefore be proven quite ineffective. This also leads to a confusing interface with needless options, models and tools that make the use of the tool difficult even for experienced users. Problems are also detected in the methodological aspect, including outdated methods and lack of the judgment component across the forecasting procedure. By exploiting exclusively free open-source solutions we indicate how a powerful FSS like OMEN can be developed offering a lot of advantages both in technological and methodologi- cal dimension. Using Shiny, R, OMEN consist an adaptable and easy to customize web-based tool enabling 24/7 access of multiple users simultaneously by the device of their choice. A simplified interface organized in comprehensive and well documented menu items facilitate its use for practitioners, while state-of-the-art algorithms, such as temporal aggregation, intermittent demand and continuous time series forecasting models, become easily available using the cutting-edge functions provided by academics and researches to the community of R.
library( 'shiny')
runGitHub( 'omen','electraa')
TarifBeat
AI project for ECE NTUA: Creating a taxi customer system for getting the closest/fastest taxi to come using a* algorithm.
ClusteringProject
The start of OMEN project. A simple app that produces forecasts for clustered data