Skip to main content

Mired in Myopia?

Reinforcement Learning (RL) deals with multi-step decision processes. One strategy for making decisions in a multi-step environment is always choose the option that maximizes your immediate payoff. In RL, they call this strategy "myopic" since it never looks beyond the payoff for the current action.

The problem is that this strategy might produce a smaller total payoff at the end of the process. If we look at the process as a whole, we may identify a sequence of actions that produces a higher overall reward while not maximizing the reward for each individual action.

This all relates to an experiment that I'm running on contact strategies. The experiment controls all calls other than appointments and refusal conversion attempts. The overall contact rate was 11.6% for the experimental protocol, and 9.0% for the control group. The difference is statistically significant.

But establishing contact is only an intermediate outcome. The final outcome of this multi-step process is completing an interview. It appears that the control and experimental groups produce interviews at about the same rate (147 control vs 153 experiment). Timestamps on the call indicate that the experimental contact strategy reduces time spent achieving the first contact by about 10%, but overall savings are only about 2% (i.e. not really different).

This looks like a case where a myopic policy (i.e. improving only the contact stage) does not lead to overall gains. The current experimental protocol will need to be expanded to all stages somehow. That's a big step...

Comments

Popular posts from this blog

The Cost of a Call Attempt

We recently did an experiment with incentives on a face-to-face survey. As one aspect of the evaluation of the experiment, we looked at the costs associated with each treatment (i.e. different incentive amounts).

The costs are a bit complicated to parse out. The incentive amount is easy, but the interviewer time is hard. Interviewers record their time for at the day level, not at the housing unit level. So it's difficult to determine how much a call attempt costs.

Even if we had accurate data on the time spent making the call attempt, there would still be all the travel time from the interviewer's home to the area segment. If I could accurately calculate that, how would I spread it across the cost of call attempts? This might not matter if all I'm interested in is calculating the marginal cost of adding an attempt to a visit to an area segment. But if I want to evaluate a treatment -- like the incentive experiment -- I need to account for all the interviewer costs, as best…

Goodhart's Law

I enjoy listening to the data skeptic podcast. It's a data science view of statistics, machine learning, etc. They recently discussed Goodhart's Law on the podcast. Goodhart's was an economist. The law that bears his name says that "when a measure becomes a target, then it ceases to be a good measure." People try and find a way to "game" the situation. They maximize the indicator but produce poor quality on other dimensions as a consequence. The classic example is a rat reduction program implemented by a government. They want to motivate the population to destroy rats, so they offer a fee for each rat that is killed. Rather than turn in the rat's body, they just ask for the tail. As a result, some persons decide to breed rats and cut off their tails. The end result... more rats.

I have some mixed feelings about this issue. There are many optimization procedures that require some single measure which can be either maximized or minimized. I think thes…

Training for Paradata

Paradata are messy data. I've been working with paradata for a number of years, and find that there are all kinds of issues. The data aren't always designed with the analyst in mind. They are usually a by-product of a process. The interviewers aren't focused (and rightly so) on generating high-quality paradata. In many situations, they sacrifice the quality of the paradata in order to obtain an interview.

The good thing about paradata is that analysis of paradata is usually done in order to inform specific decisions. How should we design the next survey? What is the problem with this survey? The analysis is effective if the decisions seem correct in retrospect. That is, if the predictions generated by the analysis lead to good decisions.


If students were interested in learning about paradata analysis, then I would suggest that they gain exposure to methods in statistics, machine learning, operations research, and an emerging category "data science." It seems like…