European Journal of Molecular & Clinical Medicine

Nowadays, the usage of internet based applications and services are widely used such as
travelling, food ordering, shopping, shipping, etc. In this paper, we propose Deep queue learning
method for predicting and ranking of online food ordering delivery applications. Online website
and mobile applications are available commercially deliver the food and provides variety of
discounts. In this work, we cluster the food and rank based on customer reviews, ordering/delivery
time, user satisfaction and cost. Ranking is done by using Association rule mining for food items
placing, repetitive orders and making places. The objective behind this how this platform is more
useful for customer as well as suppliers. We take opinion poll from customers and suppliers that is
also considered for comparison. The technology are growing rapidly some system is needed for
monitoring online processing and applications. We use Google TensorFlow for analyzing and
predicting the performance of online food ordering and delivery applications. Deep queue learning
model is proposed for applying our input attributes and Python API code for testing accuracy. The
trained and test dataset is collected from various applications. Reviews and opinion is also taken
into account. For these inputs we create deep convolutationl neural network model for making
effective decisions. The results and ranking are calculated by using TensforFlow and performance
is compared.