Dynamic Trust Evaluation Model for Online Transaction Based on Time-Frame

The existing trust evaluation system do not provide adequate support to cope with quick change in users´ behavior and falsification, so a new model based on time-frame is introduced. The model takes into account the impact of the time factor to the trust evaluation. There are four parameters in computing credibility: evaluation credibility, short-time-trust, long-time-trust, and cumulative-negative-trust. However, evaluation credibility can effectively reduce the impact of fake evaluations to the value of calculation. And short-time-trust and long-time-trust make the final evaluation results are more realistic and more reliable. The cumulative-negative-trust can punish the sellers who are dishonest. Practical application shows that the dynamic trust evaluation model based on time-frame can effectively reduce the detrimental effect, which is caused by large of false transactions in a short time.