1) A client asks your company in order to develop a system for classification problem (for example: medical insurance fraud detection). Because of user requirements, he requires the final developed system to be able to offer the explanations about system result (that says how the system result is produced). The design team suggest a BP neural network system for this application. Explain in case, you agree that it will be an effective approach to the problem?

2) In the class, we introduced different factors that generally affect the group process and outcome, like group size and the status effect. How about the levels of the familiarity among the group members in traditional face-to-face groups without the GSS support? In other words, do you think different levels of familiarity among the members in a group may affect the group process and the outcome? Provide the explanation for why or why not?