Broadly, there are 3 types of Machine Learning Algorithms.. 1. Supervised LearningHow it works: This algorithm consist of a target / outcome variable (or dependent variable) which is to be predicted from a given set of predictors (independent variables). Using these set of variables, we generate a function that map inputs to desired outputs. The training process continues until the model achieves a desired level of accuracy on the training data. Examples of Supervised Learning: Regression,Decision Tree, Random Forest, KNN, Logistic Regression etc. 2. Unsupervised LearningHow it works:In this algorithm, we do not have any target or outcome variable to predict / estimate. It is used for clustering population in different groups, which is widely used for segmenting customers in different groups for specific intervention.

Much of AI has been led by the'Big Data' movement and Graphics Processing Units (GPUs) that have transformed data processing to make it more efficient with a faster processing time. Machine Learning came about in the 1980s, and this can be viewed as an approach to AI. Its basic premise relies on using algorithms to analyze data, gather learning, and then make a prediction. Rather than hand coding or scripting to achieve a task, a machine is trained to learn how to perform it by feeding it with a large amount of data and algorithms. Machine Learning Algorithms employ decision tree learning, clustering, and Bayesian Networks, and more.

In many real-world classification tasks such as churn prediction and fraud detection, we often encounter the class imbalance problem, which means one class is significantly outnumbered by the other class. The class imbalance problem brings great challenges to standard classification learning algorithms. Most of them tend to misclassify the minority instances more often than the majority instances on imbalanced data sets. For example, when a model is trained on a data set with 1% of instances from the minority class, a 99% accuracy rate can be achieved simply by classifying all instances as belonging to the majority class. Indeed, the problem of learning on imbalanced data sets is considered to be one of the ten challenging problems in data mining research.

This is a sample of the data science projects I have been working on my own. The Zika Project, is an extensive analysis of microcephaly cases related to Zika in Brazil. This case study tries to explain how weather conditions from January 2015 to May 2016, projected 2015 and 2016 total population of men and women within a reproductive age (15- 44), prevalence of microcephaly cases, growth rate of microcephaly, and sanitation and demographic characteristics of the 27 Brazilian states have influenced the increase of microcephaly confirmed reported cases linked to zika from February 2016 to May 2016. To describe and report variables/features with greater emphasis on microcephaly, the study uses linear regression, lasso and ridge regression, regression trees, random forest regression and gradient boosting regressor. This is analysis unveils what factors other than elevation and runners split's strategy are better predictors of finishing within the top 15 male and female runners of the 2016 Boston Marathon In this short analysis explains, I used a expanded version of the mincer equation and find that marital status, gender, student's province of residence and country where student pursued his/her postgraduate studies are complementary features to explain the return of income/investement.

Facebook uses machine learning and ranking models to deliver the best experiences across many different parts of the app, such as which notifications to send, which stories you see in News Feed, or which recommendations you get for Pages you might want to follow. To surface the most relevant content, it's important to have high-quality machine learning models. We look at a number of real-time signals to determine optimal ranking; for example, in the notifications filtering use case, we look at whether someone has already clicked on similar notifications or how many likes the story corresponding to a notification has gotten. Because we perform this every time a new notification is generated, we want to return the decision for sending notifications as quickly as possible. More complex models can help improve the precision of our predictions and show more relevant content, but the trade-off is that they require more CPU cycles and can take longer to return results.

There is a large literature explaining why AdaBoost is a successful classifier. The literature on AdaBoost focuses on classifier margins and boosting's interpretation as the optimization of an exponential likelihood function. These existing explanations, however, have been pointed out to be incomplete. A random forest is another popular ensemble method for which there is substantially less explanation in the literature. We introduce a novel perspective on AdaBoost and random forests that proposes that the two algorithms work for similar reasons. While both classifiers achieve similar predictive accuracy, random forests cannot be conceived as a direct optimization procedure. Rather, random forests is a self-averaging, interpolating algorithm which creates what we denote as a "spikey-smooth" classifier, and we view AdaBoost in the same light. We conjecture that both AdaBoost and random forests succeed because of this mechanism. We provide a number of examples and some theoretical justification to support this explanation. In the process, we question the conventional wisdom that suggests that boosting algorithms for classification require regularization or early stopping and should be limited to low complexity classes of learners, such as decision stumps. We conclude that boosting should be used like random forests: with large decision trees and without direct regularization or early stopping.

-- Daytime hypoglycemia should be accurately predicted to achieve normo glycemia and to avoid disastrous situations . Hypoglycemia, an abn ormally low blood glucose level, is divided into daytime hypogly cemia and nocturnal hypoglycemia . In this paper, we propose new predictor variables to predict daytime hypoglycemia using continuous glucose monitoring (CGM) data. We apply classification and regression tree (CART) as a prediction method . The evaluation results showed that our model wa s able to detect almost 80% of hypoglycemic events 15 min in advance, which was higher than the existing methods with similar conditions . T he proposed method might achieve a real - tim e prediction as well as can be e mbedded into BG monitoring device. Diabetes is one of the most common chronic diseases in the world, affecting 2.72 million individuals (10% of the population) in the Korea [1] and 29.1 million individuals (9.3% of the populat ion) in the USA with increasing incidence [2] . Diabetes can be th e cause of kidney failure, lower - limb amputations, and blindness among adults [2] . A chievement of excellent glycemia is most important task to diabetic patients in both type 1 and type 2 diabetes. D iabetic patient s should maintain euglycemic blood glucose (BG) levels while all day and be required the wisdom to avoid hyper - and hyp oglycemia [3] . Especially, the patients who treated w ith an insulin are at risk for developing hypoglycemia. Population - based data indicate that 30 - 40% o f people with type 1 diabetes ex perience an average of three episodes of severe hypoglycemia each year; those with insulin - treated type 2 diabetes experience about one episode of that each year. Also, individuals with type 1 diabetes experienced about 43 symptomatic (not only severe) episodes annually; insulin - treated individuals with type 2 diabetes experienced about 16 episodes annually [4] . The s ymptomatic hypoglycemic e pisode mean s that the patients feel the symptoms of s hakiness, sweating, hunger, irritability or headache [5] . H ypoglycemia is a significant challenge for a precise insulin therapy [6] .

Within machine learning, the supervised learning field aims at modeling the input-output relationship of a system, from past observations of its behavior. Decision trees characterize the input-output relationship through a series of nested $if-then-else$ questions, the testing nodes, leading to a set of predictions, the leaf nodes. Several of such trees are often combined together for state-of-the-art performance: random forest ensembles average the predictions of randomized decision trees trained independently in parallel, while tree boosting ensembles train decision trees sequentially to refine the predictions made by the previous ones. The emergence of new applications requires scalable supervised learning algorithms in terms of computational power and memory space with respect to the number of inputs, outputs, and observations without sacrificing accuracy. In this thesis, we identify three main areas where decision tree methods could be improved for which we provide and evaluate original algorithmic solutions: (i) learning over high dimensional output spaces, (ii) learning with large sample datasets and stringent memory constraints at prediction time and (iii) learning over high dimensional sparse input spaces.

Data science and machine learning have long been interests of mine, but now that I'm working on Fuzzy.ai and trying to make AI and machine learning accessible to all developers, I need to keep on top of all the news in both fields. My preferred way to do this is through listening to podcasts. I've listened to a bunch of machine learning and data science podcasts in the last few months, so I thought I'd share my favorites: Every other week, they release a 10–15 minute episode where hosts, Kyle and Linda Polich give a short primer on topics like k-means clustering, natural language processing and decision tree learning, often using analogies related to their pet parrot, Yoshi. This is the only place where you'll learn about k-means clustering via placement of parrot droppings. Hosted by Katie Malone and Ben Jaffe of online education startup Udacity, this weekly podcast covers diverse topics in data science and machine learning: teaching specific concepts like Hidden Markov Models and how they apply to real-world problems and datasets.

Improving the precision of heart diseases detection has been investigated by many researchers in the literature. Such improvement induced by the overwhelming health care expenditures and erroneous diagnosis. As a result, various methodologies have been proposed to analyze the disease factors aiming to decrease the physicians practice variation and reduce medical costs and errors. In this paper, our main motivation is to develop an effective intelligent medical decision support system based on data mining techniques. In this context, five data mining classifying algorithms, with large datasets, have been utilized to assess and analyze the risk factors statistically related to heart diseases in order to compare the performance of the implemented classifiers (e.g., Na\"ive Bayes, Decision Tree, Discriminant, Random Forest, and Support Vector Machine). To underscore the practical viability of our approach, the selected classifiers have been implemented using MATLAB tool with two datasets. Results of the conducted experiments showed that all classification algorithms are predictive and can give relatively correct answer. However, the decision tree outperforms other classifiers with an accuracy rate of 99.0% followed by Random forest. That is the case because both of them have relatively same mechanism but the Random forest can build ensemble of decision tree. Although ensemble learning has been proved to produce superior results, but in our case the decision tree has outperformed its ensemble version.