My first post on using machine learning for financial prediction took an in-depth look at various feature selection methods as a data pre-processing step in the quest to mine financial data for profitable patterns. I looked at various methods to identify predictive features including Maximal Information Coefficient (MIC), Recursive Feature Elimination (RFE), algorithms with built-in feature selection, selection via exhaustive search of possible generalized linear models, and the Boruta feature selection algorithm. I personally found the Boruta algorithm to be the most intuitive and elegant approach, but regardless of the method chosen, the same features seemed to keep on turning up in the results. In this post, I will take this analysis further and use these features to build predictive models that could form the basis of autonomous trading systems. Firstly, I'll provide an overview of the algorithms that I have found to generally perform well on this type of machine learning problem as well as those algorithms recommended by David Aronson (2013) in Statistically Sound Machine Learning for Algorithmic Trading of Financial Instruments (SSML). I'll also discuss a framework for measuring the performance of various models to facilitate robust comparison and model selection. Finally, I will discuss methods for combining predictions to produce ensembles that perform better than any of the constituent models alone.

Jurgi Camblong plans to work with "liquid biopsies" making the process less invasive and faster This article was first published in the June 2016 issue of WIRED magazine. Be the first to read WIRED's articles in print before they're posted online, and get your hands on loads of additional content by subscribing online. Jurgi Camblong is diagnosing cancer using thousands of people's DNA. The 38-year-old Sophia Genetics co-founder detects cancer in the lungs, skin, ovaries and breast, as well as congenital diseases, by sequencing the genomes of patient's tissue samples – then uses machine learning to compare the results and suggest the most effective treatments. "The problem is not producing the content or the data but really analysing to find the important information so you can act on a disease," says Camblong.

Our motive is to create a simple to integrate "Machine Learning" platform but yet powerful enough to provide high accuracy and low latency API. Such a system provides Data Mining, Machine Learning and Artificial Intelligence algorithms as a service. The system has ability to create training model for datasets uploaded as a training set and performs classification on similar datasets in the future using the saved models. "Sentiment analysis (also known as opinion mining) refers to the use of natural language processing, text analysis and computational linguistics to identify and extract subjective information in source materials." Download the sample "sentiment analysis" file Sentiment Analysis The first column should always be the label to be predicted.

In statistics, ordinal regression (also called "ordinal classification") is a type of regression analysis used for predicting an ordinal variable, i.e. a variable whose value exists on an arbitrary scale where only the relative ordering between different values is significant. It can be considered an intermediate problem in between (metric) regression and classification.[1] Ordinal regression turns up often in the social sciences, for example in the modeling of human levels of preference (on a scale from, say, 1–5 for "very poor" through "excellent"), as well as in information retrieval. In machine learning, ordinal regression may also be called ranking learning.[2][a] Ordinal regression can be performed using a generalized linear model (GLM) that fits both a coefficient vector and a set of thresholds to a dataset.

Facebook CEO, Mark Zuckerberg says that within five to 10 years, artificial intelligence could advance to the point where computers can see, hear and understand language better than people. Zuckerberg stated this yesterday during the company's earnings call for the first quarter of 2016. Zuckerberg has already been focussing on AI through his company which already has research groups dedicated to advancing the company's capabilities in artificial intelligence, machine learning, computer vision and natural language processing and speech. Earlier this month, for example, it introduced an iOS feature called "automatic alternative text" that uses object recognition technology to provide spoken descriptions of Facebook photos to people who are visually impaired. Facebook has also unveiled new bot and chatbot technology as part of its Messenger Platform.

NEW ORLEANS--The problem with robots on the battlefield today, according to Marine Corps Colonel Jim "Jinx" Jenkins, is that they still have to be driven by humans. That's why the Marine Corps and the Department of Defense are researching ways for robots to act more like teammates on the battlefield than just another piece of hardware. Jenkins, who serves as director of science and technology at the Marine Corps' Warfighting Lab at Quantico, Virginia, said in a presentation at the Association for Unmanned Systems International's XPONENTIAL conference that while robots such as those used for explosive ordnance disposal and other roles on the battlefield take soldiers and Marines out of some dangerous situations, they take their operators out of the fight. "A marine is driving, so we haven't improved our manpower situation, and sometimes it costs more manpower," he noted, since operators have to pay such close attention to what they're doing with the robot that they need someone watching their back. "We need to move toward autonomy" for robots and other uncrewed systems, he said.

DATAVERSITY Education, LLC announced the agenda and opened registration for the company's newest online conference, Smart Data Online (SDO). The event will be held online at smartdataweek.com on July 13th, 2016 from 8:00 am to 2:20 pm Pacific Time. Registration is free and attendees will receive access to the on demand recordings, slides, and materials following the event. SDO is the newest event to be added to DATAVERSITY's educational programs, and is designed to provide guidance on executing and implementing a successful data strategy using new technologies in the fields of machine learning, cognitive computing, and artificial intelligence. Throughout the day on July 13th there will be six, 40-minute presentations, each followed by a 10 minute "Q & A" discussion with the presenter(s).

Watch our founder and CEO, Parsa Ghaffari (@parsaghaffari) and Kevin Koidl (@koidl), a Research Fellow at Trinity College Dublin's Department of Computer Science and the ADAPT research centre, talk Computer intelligence at a recent talk they gave at Science Gallery, Dublin. This interactive discussion, takes you from general AI, right through to the modern day applications of narrow AI paying, particular attention to a real life example, the Bigfoot App, which was created as part of the Lifelogging exhibition, currently running at Science Gallery, Dublin.

In this post I will explain the Support Vector Machines method. First, what is a Support Vector? It's the margins of an Hyperplane (linear or not) that divides two or more groups, whose margin (distance between two groups) must be maximized: The Hyperplane borders are H1 and H2 and the distance to be maximized is d1 and d2. First, let's do a regular Linear Regression with black dots (X1) and white dots (X2). You can easily see that the estimated Y (red line) barely touches some of the blue dots (real Y).

For all of Amazon's grand plans regarding delivery drones, it still needs to figure out concepts we take for granted with traditional courier methods. Namely, figuring out how to drop off your latest order without destroying anything (including the UAV itself) during transit and landing. That's where advanced computer vision comes in from Jeff Bezos' new team of Austria-based engineers, according to The Verge. The group invented methods for reconstructing geometry from images and contextually recognizing environmental objects, giving the drones the ability to differentiate between, say, a swimming pool and your back patio. Both are flat surfaces, but one won't leave your PlayStation VR headset waterlogged after drop-off.