Adaptive Probabilistic Behavioural Learning System for the effective behavioural decision in cloud trading negotiation market

• Bilateral negotiation process is modelled as the multi-stage Markov decision problem.
• Adaptive Probabilistic Behavioural Learning analyse offer using inference engine.
• Operational view of proposed learning tactics is modelled as layered data flow graph.
• Flow graph predicts behavioural tactics and suggest counter tactics from rule base.
• Behavioural decision making heuristic is based on the probability distribution.

In cloud e-commerce application, building an automated negotiation strategy by understanding the uncertain information of the opponent preferences, utilities, and tactics is highly challenging. The key issue is to analyse and predict the uncertain behaviour of the opponent tactics to suggest the appropriate counter tactics that can reach maximum consensus. To handle such uncertain information, negotiation strategies follow several tactics with and without learning ability. Strategies without learning ability are restricted to negotiate with the opponent having only deterministic behaviour. To overcome this problem most researchers exploited the negotiation strategies with fixed learning ability using Bayesian learning, neural network learning, and genetic tactics. These tactics can learn the opponent’s behaviour and cannot guarantee to generate suitable counter-offer for all offers submitted by the opponent cloud service provider. This limitation motivates to propose a novel Adaptive Probabilistic Behavioural Learning System for managing the opponent having unpredictable random behaviours. The proposed Adaptive Probabilistic Behavioural Learning System contains a Behavioural Inference Engine to analyse the sequence of negotiation offer received by the broker for effectively learning the opponent’s behaviour over several stages of negotiation process. It also formulates the multi-stage Markov decision problem to suggest the broker with appropriate counter-offer behavioural tactics generation based on the adaptive probabilistic decision taken over the corresponding negotiation stage. Therefore, this research work can outperform the existing fixed behavioural learning tactics and hence maximize the utility value and success rate of negotiating parties without any break-off.