# Assigning Weighting Factors

I have a hypothetical example that closes to my research problem:

Assume you are a boss and you have different types of tasks that you need to assign to your employee. Sensitive task (very classified), and task that requires high skills. So you need to assign a sensitive task (government document) to the trusted employee. While the other task (e.g. statistical analysis ) can be assigned to employee who is more creative and smart. Now every day you have many tasks that need to be done and have a large number of employees with a number of crowdsources (freelancers).

You have an outcome and history of trust and performance along of failure rate of assigned task on that day of these employees as:

As you can see here on day 1: the trust of emp 111 is good, so on that day, he had a low failure rate of the sensitive task. While his performance is low, and that made other task failed a lot.

So now assume you have a sensitive task coming, and you have a pool of workers.

The basic equation might not good here: Trust + Performance. I need to weigh each factor based on the type of tasks.

Trust x w1 + performance x w2 ::::: w1 is high coefficient when sensitive is coming.

Any idea of how I model these issues.

• I think recommender systems or clustering are a good solution to your problems, I can't detail the answer as I haven't worked on the aforementioned systems, but they are good algos for unsupervised learning tasks like the one defined above. – DuttaA Oct 17 '19 at 6:53
• Thank you for the clarification – jou Oct 17 '19 at 9:06
• Can I use the analytic hierarchy process (AHP)? – jou Oct 17 '19 at 21:46