[thejbills]

Running the max and min numbers.

Max score
Max regression score: 1.0
Max classification score: 1.0
Max total score: 1.0

Min score
Min regression score: 0
Min classification score: -5.0
Min total score: -2.5

[thejbills]

Use
[email protected]

[thejbills]

Please just email us the request with the new team memeber’s information.

[thejbills]

Hi Qin,

As stated in the main description “Classification and regression predictions will be scored separately, and the final score is the mean score of all predictions.”

[thejbills]

Design torque is not a measured variable, thus it’s not in the X_train.csv (features) file. And the goal is to predict the torque margin which is a function of the design torque. Torque margin is given in the y_train.csv (targets) file.

[thejbills]

Our scoring function actually uses the parameters you supply including the scale (I’ll update the description language). But the scoring functions corrects area and peak probability.

If the area is not 1 it’s normalized to 1.
Then
If the max probability is greater than 1, it’s normalized to one.

[thejbills]

From the data challenge problem descrition page

Each engine is instrumented to capture the outside air temperature, mean gas temperature, power available, indicated airspeed, net power, and compressor speed.

oat = outside air temperature
mgt = mean gas temperature
pa = power available
ias = indicated airspeed
np = net power
ng = compressor speed (that one’s not as obvious)

[thejbills]

FYI, the leader board is up. All participants should have recieved an email notifying them.

[thejbills]

There is. We originaly had 6 engines, but we were able to get another one. There are 4 engines in the training dataset.

[thejbills]

There is. We originaly had 6 engines, but we were able to get another one. There are 4 engines in the training dataset.

[thejbills]

You are correct!

The idea is to strongly penalize predicting that the engine is okay when infact it’s not. This is a false negative.

For the reference of others reading this.

Positive refers to the faulty state
Negative referes to the healty state

False positive = predicting faulty engine when it is healthy
False negative = predicting healthy engine when it is faulty

[thejbills]

What we’ve shown on the webpage is generic. Please use the id that aligns with the observation in each file.

[thejbills]

It’s not up yet! There have been some delays. I’ll see where we stand at try to get it up and running.

[thejbills]

Hi Hanqisu,

We are further pursuing methods of explainability this year. Last year, we had participants submit a discreet distribution with a confidence metric. This year, we are building on that to ask for a continuous distribution (which is required for a regression analysis). As indicated in the writeup, the scoring algorithm evaluates the probability of your estimate at the exact torque margin.

If you like, we can incorporate a delta function, which will allow you to submit an exact value. However, if this value is off even by a little, you’ll get a score of 0 because you’ll have predicted a probability of zero. If you consider the problem, there are better ways to submit a PDF that will give you a better chance (and get closer to what you’re trying to achieve).

[thejbills]

imp101, you are not a registered participant. Thus you don’t have access to the submission page. We have received some registration request with incorrect user names and email addresses. If you have already tried to register, it is possible that one of these was your registration. Please submit a registration with the same username and email address that you use for the phmsociety.org site.

[Author]

Posts