Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Preface Chapter 1 The challenge Chapter 2 The nature of the evidence: A synthesis of meta-analyses Chapter 3 The argument: Visible teaching and visible learning Chapter 4: The contributions from the student Chapter 5 The contributions from the home Chapter 6 The contributions from the school Chapter 7 The contributions from the teacher Chapter 8 The contributions from the curricula Chapter 9 The contributions from teaching approaches - I Chapter 10 The contributions from teaching approaches - II Chapter 11: Bringing it all together Appendix A: The 800 meta-analyses Appendix B: The meta-analyses by rank order References

Visible Learning: A Synthesis of Over 800 Meta-Analyses Relating to Achievement

Video games are a ubiquitous part of almost all children's and adolescents' lives, with 97% playing for at least one hour per day in the United States. The vast majority of research by psychologists on the effects of "gaming" has been on its negative impact: the potential harm related to violence, addiction, and depression. We recognize the value of that research; however, we argue that a more balanced perspective is needed, one that considers not only the possible negative effects but also the benefits of playing these games. Considering these potential benefits is important, in part, because the nature of these games has changed dramatically in the last decade, becoming increasingly complex, diverse, realistic, and social in nature. A small but significant body of research has begun to emerge, mostly in the last five years, documenting these benefits. In this article, we summarize the research on the positive effects of playing video games, focusing on four main domains: cognitive, motivational, emotional, and social. By integrating insights from developmental, positive, and social psychology, as well as media psychology, we propose some candidate mechanisms by which playing video games may foster real-world psychosocial benefits. Our aim is to provide strong enough evidence and a theoretical rationale to inspire new programs of research on the largely unexplored mental health benefits of gaming. Finally, we end with a call to intervention researchers and practitioners to test the positive uses of video games, and we suggest several promising directions for doing so.

/pdf/the-benefits-of-playing-video-games-4khoewx5le.pdf

The benefits of playing video games

It is assumed that serious games influences learning in 2 ways, by changing cognitive processes and by affecting motivation. However, until now research has shown little evidence for these assumptions. We used meta-analytic techniques to investigate whether serious games are more effective in terms of learning and more motivating than conventional instruction methods (learning: k = 77, N 5,547; motivation: k = 31, N 2,216). Consistent with our hypotheses, serious games were found to be more effective in terms of learning (d= 0.29, p .05) than conventional instruction methods. Additional moderator analyses on the learning effects revealed that learners in serious games learned more, relative to those taught with conventional instruction methods, when the game was supplemented with other instruction methods, when multiple training sessions were involved, and when players worked in groups.

/pdf/a-meta-analysis-of-the-cognitive-and-motivational-effects-of-2hxl2cnuc5.pdf

A meta-analysis of the cognitive and motivational effects of serious games

The purpose of this meta-analysis is to examine overall effect as well as the impact of selected instructional design principles in the context of virtual reality technology-based instruction (i.e. games, simulation, virtual worlds) in K-12 or higher education settings. A total of 13 studies (N?=?3081) in the category of games, 29 studies (N?=?2553) in the category of games, and 27 studies (N?=?2798) in the category of virtual worlds were meta-analyzed. The key inclusion criteria were that the study came from K-12 or higher education settings, used experimental or quasi-experimental research designs, and used a learning outcome measure to evaluate the effects of the virtual reality-based instruction.Results suggest games (FEM?=?0.77; REM?=?0.51), simulations (FEM?=?0.38; REM?=?0.41), and virtual worlds (FEM?=?0.36; REM?=?0.41) were effective in improving learning outcome gains. The homogeneity analysis of the effect sizes was statistically significant, indicating that the studies were different from each other. Therefore, we conducted moderator analysis using 13 variables used to code the studies. Key findings included that: games show higher learning gains than simulations and virtual worlds. For simulation studies, elaborate explanation type feedback is more suitable for declarative tasks whereas knowledge of correct response is more appropriate for procedural tasks. Students performance is enhanced when they conduct the game play individually than in a group. In addition, we found an inverse relationship between number of treatment sessions learning gains for games.With regards to the virtual world, we found that if students were repeatedly measured it deteriorates their learning outcome gains. We discuss results to highlight the importance of considering instructional design principles when designing virtual reality-based instruction. A comprehensive review of virtual reality-based instruction research.Analysis of the moderation effects of design features in a virtual environment.Using an advance statistical technique of meta-analysis to study the effects.Virtual reality environment is effective for teaching in K-12 and higher education.Results can be used by instructional designers to design the virtual environments.

Effectiveness of virtual reality-based instruction on students' learning outcomes in K-12 and higher education

Most decision tree algorithms base their splitting decisions on a piecewise constant model. Often these splitting algorithms are extrapolated to trees with non-constant models at the leaf nodes. The motivation behind Look-ahead Linear Regression Trees (LLRT) is that out of all the methods proposed to date, there has been no scalable approach to exhaustively evaluate all possible models in the leaf nodes in order to obtain an optimal split. Using several optimizations, LLRT is able to generate and evaluate thousands of linear regression models per second. This allows for a near-exhaustive evaluation of all possible splits in a node, based on the quality of fit of linear regression models in the resulting branches. We decompose the calculation of the Residual Sum of Squares in such a way that a large part of it is pre-computed. The resulting method is highly scalable. We observe it to obtain high predictive accuracy for problems with strong mutual dependencies between attributes. We report on experiments with two simulated and seven real data sets.

Scalable look-ahead linear regression trees

We organized the KDD cup 2009 around a marketing problem with the goal of identifying data mining techniques capable of rapidly building predictive models and scoring new entries on a large database. Customer Relationship Management (CRM) is a key element of modern marketing strategies. The KDD Cup 2009 offered to participants an opportunity to work on a large marketing database from the French Telecom company Orange. The tasks were to predict the propensity of customers to switch provider (churn), buy new products or services (appetency), or buy upgrades/addons proposed to them to make the sale more profitable (upselling). The challenge, which lasted from March 10 to May 11, 2009, attracted over 450 participants from 46 countries. We attribute its popularity to several factors: (1) A generic problem relevant to the Industry (a classification problem), but presenting a number of scientific and technical challenges, including many missing values (about 60%), a large number of features (15000) and a large number of training examples (50000), unbalanced class proportions (fewer than 10% of the examples of the positive class), noisy data, and the presence of categorical variables with many different values. (2) Prizes (Orange offers 10000 Euros in prizes). (3) A well designed protocol and web site (we benefitted from past experience). (4) An effective advertising campaign using mailings and a teleconference to answer potential participants questions. The results of the challenge were discussed at the KDD conference (June 28, 2009). The principal conclusions are that ensemble methods are very effective and that ensemble of decision trees offer off-the-shelf solutions to problems with large numbers of samples and attributes, mixed types of variables, and lots of missing values. The data and the platform of the challenge remain available for research and educational purposes at http://www.kddcup-orange.com/.

/pdf/design-and-analysis-of-the-kdd-cup-2009-fast-scoring-on-a-4xbmyu74ic.pdf

Design and analysis of the KDD cup 2009: fast scoring on a large orange customer database

In this paper, we describe techniques that can be used to predict the effects of gene deletion. We will focus mainly on the creation of predictive variables, and then briefly discuss different modeling techniques that have been used successfully on this data.

Predicting the effects of gene deletion

What is the difference between matter and anti-matter? A. I. Insight's winning solution on the Particle Physics Task for the 2004 KDD Cup demonstrates how an accurate predictive model can be formulated without knowledge of the content of the data. Information on the data was not available for the modeling, including a description on the outcome to be predicted. In other words, an 80 x 150,000 grid of numbers with the header "Particle Physics" was all that was given to the 500+ registrants of this competition. Key steps in creating the winning model were interactive analysis of the variables, detection of interactions, a powerful self-organizing neural network, and customization of the 4 different error criteria.

Anti-matter detection: particle physics model for KDD Cup 2004

Transformation of both the response variable and the predictors is commonly used in fitting regression models. However, these transformation methods do not always provide the maximum linear correlation between the response variable and the predictors, especially when there are non-linear relationships between predictors and the response such as the medical data set used in this study. A spline based transformation method is proposed that is second order smooth, continuous, and minimizes the mean squared error between the response and each predictor. Since the computation time for generating this spline is O(n), the processing time is reasonable with massive data sets. In contrast to cubic smoothing splines, the resulting transformation equations also display a high level of efficiency for scoring. Data used for predicting health outcomes contains an abundance of non-linear relationships between predictors and the outcomes requiring an algorithm for modeling them accurately. Thus, a transformation that fits an adaptive cubic spline to each of a set of variables is proposed. These curves are used as a set of transformation functions on the predictors. A case study of how the transformed variables can be fed into a simple linear regression model to predict risk outcomes is presented. The results show significant improvement over the performance of the original variables in both linear and non-linear models.

/pdf/1-dimensional-splines-as-building-blocks-for-improving-177q5ck4da.pdf

David S. Vogel

Papers

Scalable look-ahead linear regression trees

Design and analysis of the KDD cup 2009: fast scoring on a large orange customer database

Predicting the effects of gene deletion

Anti-matter detection: particle physics model for KDD Cup 2004

1-dimensional splines as building blocks for improving accuracy of risk outcomes models