Quick links

What has caught my attention lately:

• Difference between Machine Learning & Statistical Modeling... ([1])
• Semi-supervised learning frameworks for Python. Interesting and worth a try. ([2])
• The Present and the Future of the KDD Cup Competition. "Three main take-aways from the KDD Cup workshop presentations: XGBoost, Feature Engineering is the king and Team work is crucial." ([3])
• Comparing 7 Python data visualization tools. compare + examples. :) ([4])
• The Three Cultures of Machine Learning. ([5])
• Slides and videos from MLconf 2015, San Francisco ([6])

A short review of data science summit @ dato 2015

2015 Data Science Summit @ dato Review from Hang Li

More slides can be found in Dato, Inc.. 

Quick links

What has caught my attention lately:

• Machine Learning Table of Elements Decoded. No xgboost?! ([1])
• 6 tricks from otto challenge! ([2])
• Machine learning evaluation metrics. ([3])
• Ensembling! ([4])
• Owen(kaggle #1) talk! ([5])
• Data science ipython notebooks. ([6])
. 

Quick links

What has caught my attention lately:

• A Benchmark Dataset for Time Series Anomaly Detection. ([1])
• Python image processing libraries performance: OpenCV vs Scipy vs Scikit-Image. ([2])
• Exploring Spark MLlib. ([3])
• 7 Python Libraries you should know about ([4])
• Benchmarking random forest implementations. ([5])
• Statistical inference is only mostly wrong. (really?!) ([6])

Quick links

What has caught my attention lately:

• Distance and similarity in machine learning(Chinese). ([1])
• "How to Choose a Neural Network" from DL4J. ([2])
• Winning solution at the BCI Challenge @ NER 2015. ([3] [4])
• Winning solution of The National Data Science Bowl. Convolutional neural networks win again! A lot of techniques to prevent overfitting! ([5] [6])
• Scikit-image is a collection of algorithms for image processing. ([7])

Take away from kaggle tradeshift winner

Tradeshift competition is predicting the probability that a piece of text belongs to each of the 33 classes. Winning solutions can be found in forum thread. Code is also in git.

• Best solution is a weighted average of 14 two stage models, 13 online models and 2 simple one stage models. (blending!!!)
• Prediction of 32 labels are used as features for 2nd half of data. (Labels have strong inter-dependence!)
• Xgboost is chosen as the single metastage classifier. (Xgboost win again!)
• Not only feature analysis, but also need label analysis. 
• Feature selection for online model. 
• Heavily rely on CV and grid search to fine-tune hyper-parameters.

Some other solutions shared in forum.

• Additional (100-300) decision tree features based on Criteo's winning solution.  
• Postprocess on some labels. (o_O)
• Even 3-stages solution!
• "sklearn RandomForestClassifier active paths or ended nodes" should be useful to generate tree based features.
• Semi-supervise in blending. 

Quick links

What has caught my attention lately:

• LIBFFM: A Library for Field-aware Factorization Machines. It has been used to win two recent click-through rate prediction competitions (Criteo's and Avazu's). ([1])
• Anscombe's quartet hmm~~ :)  ([2])
• Timeseries Classification: KNN & DTW ([3] [4])
• "Outlier and Anomaly Detection In Server Instances With Machine Learning At Netflix: Cody Rioux" DBSAN + MCMC ([5])
• Introduction of python Decorators and Context Managers ([6])