The biggest issue I see from the ivory tower I'm surrounded by is that economists typically doubt the results of data mining. Neural networks, machine learning, etc. are all well known toolkits in computational economics (one of my specialties) but the results from their application are rarely believed.
It's really hard to tell, especially outside the field, whether someone's computation has found signal and not noise in their data series, or even whether that data series has any significance for different times and different places ...
(You can "Monte Carlo" the past as much as you want, it won't become the future.)
Edit: I probably should have just referenced Sliver's Signal and Noise and left it at that.
Structural models are more 'insightful' than generative models in machine learning. Econ guys are more interested in Pr(y|x) than reproducing the data.
That being said, I really hope computational work gains more traction... this might be a marketing issue.
