GARCH PROOF OF CONCEPT _ UPDATED 18 DEC 2008

Making sense of data may benefit from high volume data acquisition and analysis using GARCH and VAR-MGARCH (Datta et al 2007) techniques in addition to and in combination with other tools for forecasting and risk analysis in diverse verticals that may span from healthcare to energy (Datta 2008e). In this work, we explored the possibility of using advanced forecasting methods in context of supply chains and demonstrated financial profitability from use of the GARCH technique. It remains unexplored if concomitant business process transformation may be necessary to obtain even better results. The proposed advanced forecasting models, by their very construction require high volume data. Availability of high volume data may not be the limiting factor in view of the renewed interest in automatic identification technologies (AIT) that may facilitate acquisition of real-time data from products or objects with RFID tags or embedded sensors. It is no longer a speculation but based on proof that use of advanced forecasting methods may enhance profitability and ICT investments required to acquire real-time data may generate significant return on investment (ROI). However, understanding the “meaning” of the information from data is an area still steeped in quagmire but may begin to experience some clarity if the operational processes take advantage of the increasing diffusion of the semantic web and organic growth of ontological frameworks to support ambient intelligence in decision systems coupled to intelligent agent networks (Datta 2006). To move ahead, we propose to bolster the GARCH proof of concepts through pilot implementations of analytical engines in diverse verticals and explore advanced forecasting models as an integrated part and parcel of real-world business processes and systems including the emerging field of carbonomics (Datta 2008f).