Machine Learning: predictive model for service disruptions to be implemented in Spark-Scala

Predict service faults in a telecommunications network. Data sets will be provided to descent proposals.

The evaluation must be done as following and should be part of the program to be written. And score should be less than 0.50002.

Submissions are evaluated using the multi-class logarithmic loss. Each data row has been labeled with one true class. For each row, you must submit a set of predicted probabilities (one for every fault severity). The formula is then,

logloss=−1N∑i=1N∑j=1Myijlog(pij),

where N is the number of rows in the test set, M is the number of fault severity classes, log is the natural logarithm, yij is 1 if observation i belongs to class j and 0 otherwise, and pij is the predicted probability that observation i belongs to class j.

The submitted probabilities for a given row are not required to sum to one because they are rescaled prior to being scored (each row is divided by the row sum). In order to avoid the extremes of the log function, predicted probabilities are replaced with max(min(p,1−10−15),10−15).

机器学习（ML） Spark Scala

项目ID： #20296476

关于项目