Regression (PR) trees, that adapt to the smoothness of the prediction function relating input and output variables while preserving the interpretability of the prediction and being robust to noise. In PR trees, an observation is associated to all regions of a tree through a probability distribution that reflects how far the observation is to a region.

This paper analyzes comparatively the performance of Random Forests and Gradient Boosting algorithms in the field of forecasting the energy consumption based on historical data. The two algorithms are applied in order to forecast the energy consumption individually, and then combined together by using a Weighted Average Ensemble Method. The comparison among the achieved experimental results proves that the Weighted Average Ensemble Method provides more accurate results than each of the two algorithms applied alone.

Apache Spark's Machine Learning Library (MLlib) is designed primarily for scalability and speed by leveraging the Spark runtime for common distributed use cases in supervised learning like classification and regression, unsupervised learning like clustering and collaborative filtering and in other cases like dimensionality reduction. In this article, I cover how we can use SHAP to explain a Gradient Boosted Trees (GBT) model that has fit our data at scale. Before we understand what Gradient Boosted Trees are, we need to understand boosting. Boosting is an ensemble technique that sequentially combines a number of weak learners to achieve an overall strong learner. In case of Gradient Boosted Trees, each weak learner is a decision tree that sequentially minimizes the errors (MSE in case of regression and log loss in case of classification) generated by the previous decision tree in that sequence.

Gradient Boosted Decision Trees (GBDTs) are widely used for building ranking and relevance models in search and recommendation. Considerations such as latency and interpretability dictate the use of as few features as possible to train these models. Feature selection in GBDT models typically involves heuristically ranking the features by importance and selecting the top few, or by performing a full backward feature elimination routine. On-the-fly feature selection methods proposed previously scale suboptimally with the number of features, which can be daunting in high dimensional settings. We develop a scalable forward feature selection variant for GBDT, via a novel group testing procedure that works well in high dimensions, and enjoys favorable theoretical performance and computational guarantees. We show via extensive experiments on both public and proprietary datasets that the proposed method offers significant speedups in training time, while being as competitive as existing GBDT methods in terms of model performance metrics. We also extend the method to the multitask setting, allowing the practitioner to select common features across tasks, as well as selecting task-specific features.

Black-box nature hinders the deployment of many high-accuracy models in medical diagnosis. It is risky to put one's life in the hands of models that medical researchers do not trust. However, to understand the mechanism of a new virus, such as COVID-19, machine learning models may catch important symptoms that medical practitioners do not notice due to the surge of infected patients during a pandemic. In this work, the interpretation of machine learning models reveals that a high C-reactive protein (CRP) corresponds to severe infection, and severe patients usually go through a cardiac injury, which is consistent with well-established medical knowledge. Additionally, through the interpretation of machine learning models, we find phlegm and diarrhea are two important symptoms, without which indicate a high risk of turning severe. These two symptoms are not recognized at the early stage of the outbreak, whereas our findings are corroborated by later autopsies of COVID-19 patients. We find patients with a high N-terminal pro B-type natriuretic peptide (NTproBNP) have a significantly increased risk of death which does not receive much attention initially but proves true by the following-up study. Thus, we suggest interpreting machine learning models can offer help to diagnosis at the early stage of an outbreak.

The Gradient Boosted Tree (GBT) algorithm is one of the most popular machine learning algorithms used in production, for tasks that include Click-Through Rate (CTR) prediction and learning-to-rank. To deal with the massive datasets available today, many distributed GBT methods have been proposed. However, they all assume a row-distributed dataset, addressing scalability only with respect to the number of data points and not the number of features, and increasing communication cost for high-dimensional data. In order to allow for scalability across both the data point and feature dimensions, and reduce communication cost, we propose block-distributed GBTs. We achieve communication efficiency by making full use of the data sparsity and adapting the Quickscorer algorithm to the block-distributed setting. We evaluate our approach using datasets with millions of features, and demonstrate that we are able to achieve multiple orders of magnitude reduction in communication cost for sparse data, with no loss in accuracy, while providing a more scalable design. As a result, we are able to reduce the training time for high-dimensional data, and allow more cost-effective scale-out without the need for expensive network communication.

Scaling regression to large datasets is a common problem in many application areas. We propose a two step approach to scaling regression to large datasets. Using a regression tree (CART) to segment the large dataset constitutes the first step of this approach. The second step of this approach is to develop a suitable regression model for each segment. Since segment sizes are not very large, we have the ability to apply sophisticated regression techniques if required. A nice feature of this two step approach is that it can yield models that have good explanatory power as well as good predictive performance. Ensemble methods like Gradient Boosted Trees can offer excellent predictive performance but may not provide interpretable models. In the experiments reported in this study, we found that the predictive performance of the proposed approach matched the predictive performance of Gradient Boosted Trees.

As most of you are already aware, RapidMiner is a kick-ass platform offering pretty much everything you need for doing data science in a very efficient way. But what you don't know is that … RapidMiner Studio just got even more awesome! Wait… is this even possible? Well, it was no easy task – but we have done it: Introducing RapidMiner Studio 7.2. Let's take a look at some of the new features: We've added 4 new algorithms for machine learning, and I am still having a hard time figuring out which one I like the most: Naturally, I gave them a test run on some data sets, and was pretty freakin' impressed with the prediction accuracy, automatic tuning capabilities, and runtimes.