Generation of Hierarchy Ranking Model to Strengthen Decision Making Parameters
Prediction models are gaining popularity amongst the scientists and researchers from different domain. Till date, the utility of prediction models has been proved in majority of sectors to name a few, land use changes, growth pattern, population and infrastructure, city development plans, resources management, disaster prone areas etc. Most of the prediction models are based on multi criteria decision support system where various causative parameters are identified and suitable weights are assigned to them. The suitability of weights allotted is calculated by different methods namely Normalized Mean Value (NMV), Geometric Mean Method (GMM) and Eigen Vector Method (EVM). The computed weights assigned to causative parameters strengthen the accuracy and validity of prediction model. In present research the combination of NMV and EVM is made to calculate the most suitable weights for three land use categories namely fallow, barren and agricultural land which play key role of decision parameters in the land use prediction model. Generated output of hierarchy ranking model is further utilized as an input for decision support system based model. This design module also helps assigning the most suitable weightages to different decision support system based models.