Traditional recommender systems try to provide users with recommendations which maximize the probability that the user will accept them. Recent studies have shown that recommender systems have a positive effect on the provider’s revenue. In this paper we show that by giving a different set of recommendations, the recommendation system can further increase the business’ utility (e.g. revenue), without any significant drop in user satisfaction. Indeed, the recommendation system designer should have in mind both the user, whose taste we need to reveal, and the business, which wants to promote specific content. In order to study these questions, we performed a large body of experiments on Amazon Mechanical Turk. In each of the experiments, we compare a commercial state-of-the-art recommendation engine with a modified recommendation list, which takes into account the utility (or revenue) which the business obtains from each suggestion that is accepted by the user. We show that the modified recommendation list is more desirable for the business, as the end result gives the business a higher utility (or revenue). To study possible longterm effects of giving the user worse suggestions, we asked the users how they perceive the list of recommendation that they received. Our findings are that any difference in user satisfaction between the list is negligible, and not statistically significant. We also uncover a phenomenon where movie consumers prefer watching and even paying for movies that they have already seen in the past than movies that are new to them.

Detection of cognitive impairment, especially at the early stages, is critical. Such detection has traditionally been performed manually by one or more clinicians based on reports and test results. Machine learning algorithms offer an alternative method of detection that may provide an automated process and valuable insights into diagnosis and classification. In this paper, we explore the use of neuropsychological and demographic data to predict Clinical Dementia Rating (CDR) scores (no dementia, very mild dementia, dementia) and clinical diagnoses (cognitively healthy, mild cognitive impairment, dementia) through the implementation of four machine learning algorithms, naïve Bayes (NB), C4.5 decision tree (DT), back-propagation neural network (NN), and support vector machine (SVM). Additionally, a feature selection method for reducing the number of neuropsychological and demographic data needed to make an accurate diagnosis was investigated. The NB classifier provided the best accuracies, while the SVM classifier proved to offer some of the lowest accuracies. We also illustrate that with the use of feature selection, accuracies can be improved. The experiments reported in this paper indicate that artificial intelligence techniques can be used to automate aspects of clinical diagnosis of individuals with cognitive impairment.

Some of the most successful Poker agents that participate in the Annual Computer Poker Competition (ACPC) use an almost zero regret strategy: a strategy that approximates a Nash Equilibrium. However, it is still unfeasible to efficiently compute a Nash Equilibrium without some sort of information set abstraction due to the size of Poker’s search tree. One popular technique for abstracting Poker information sets is to group hands with similar Expected Hand Strength ( E [ HS ]) and thus play them in the same way. For large Poker variants, algorithms like CFR might need to calculate E [ HS ] billions of times, when the game abstraction is so large that it cannot be pre-computed, implying that E [ HS ] must be determined online. This way, improving the efficiency of this method would certainly reduce the computation time needed by CFR for these cases. In this paper we describe Average Rank Strength; a technique based on a pre-computed lookup table that speeds up E [ HS ] computation. Ours results demonstrate speed improvements of about three orders of magnitude and negligible results difference, when compared to the original E [ HS ].

Unplanned hospital readmissions raise health care costs and cause significant distress to patients. Hence, predicting which patients are at risk to be readmitted is of great interest. In this paper, we mine large amounts of administrative information from claim data, including patients demographics, dispensed drugs, medical or surgical procedures performed, and medical diagnosis, in order to predict readmission using supervised learning methods. Our objective is to gain knowledge about the predictive power of the available information. Our preliminary results on data from the provincial hospital system in Quebec illustrate the potential for this approach to reveal important information on factors that trigger hospital readmission. Our findings suggest that a substantial portion of readmissions is inherently hard to predict. Consequently, the use of the raw readmission rate as an indicator of the quality of provided care might not be appropriate.

My work aims to create a scaffold for deployable intelligent systems using crowdsourcing. Current approaches in artificial intelligence (AI) typically focus on solving a narrow subset of problems in a given space - for example: automatic speech recognition as part of a conversational assistant, machine vision as part of a question answering service for blind people, or planning as part of a home assistive robot. This approach is necessary to scope the solution, but often results in a large number of systems that are rarely deployed in real-world setting, but instead operate in toy domains, or in situations where other parts of the problem are assumed to be solved. The framework I have developed aims to use the crowd to help in two ways: (i) make it possible to use human intelligence to power parts of a system that automated approaches cannot or do not yet handle, and (ii) provide a means of enabling more effective deployable systems by people to provide reliable training data on-demand. This summary begins with a brief review of prior work, then outlines a number of different system that I have developed to demonstrate the capabilities of this framework, and concludes with future work to be completed as part of my thesis.

Learning from imbalanced data is an important problem in data mining research. Much research has addressed the problem of imbalanced data by using sampling methods to generate an equally balanced training set to improve the performance of the prediction models, but it is unclear what ratio of class distribution is best for training a prediction model. Bagging is one of the most popular and effective ensemble learning methods for improving the performance of prediction models; however, there is a major drawback on extremely imbalanced data-sets. It is unclear under which conditions bagging is outperformed by other sampling schemes in terms of imbalanced classification. These issues motivate us to propose a novel approach, unevenly balanced bagging (UBagging) to boost the performance of the prediction model for imbalanced binary classification. Our experimental results demonstrate that UBagging is effective and statistically significantly superior to single learner decision trees J48 (SingleJ48), bagging, and equally balanced bagging (BBagging) on 32 imbalanced data-sets.

Efficient reasoning in large knowledge bases is an important problem for AI systems. Hand-optimization of reasoning becomes impractical as KBs grow, and impossible as knowledge is automatically added via knowledge capture or machine learning. This paper describes a method for automatic extraction of axioms for efficient inference over large knowledge bases, given a set of query types and information about the types of facts in the KB currently as well as what might be learned. We use the highly right skewed distribution of predicate connectivity in large knowledge bases to prune intractable regions of the search space. We show the efficacy of these techniques via experiments using queries from a learning by reading system. Results show that these methods lead to an order of magnitude improvement in time with minimal loss in coverage.

Motivated by the problem of building a basic reasoner for general game playing with imperfect information, we address the problem of filtering with logic programs, whereby an agent updates its incomplete knowledge of a program by observations. We develop a filtering method by adapting an existing backward-chaining and abduction method for so-called open logic programs. Experimental results show that this provides a basic effective and efficient "legal" player for general imperfect-information games.

In this paper we apply AI planning to address the hypothesis exploration problem and provide assistance to network administrators in detecting malware based on unreliable observations derived from network traffic.Building on the already established characterization and use of AI planning for similar problems, we propose a formulation of the hypothesis generation problem for malware detection as an AI planning problem with temporally extended goals and actions costs. Furthermore, we propose a notion of hypothesis ``plausibility'' under unreliable observations, which we model as plan quality. We then show that in the presence of unreliable observations, simply finding one most ``plausible'' hypothesis, although challenging, is not sufficient for effective malware detection. To that end, we propose a method for applying a state-of-the-art planner within a principled exploration process, to generate multiple distinct high-quality plans. We experimentally evaluate this approach by generating random problems of varying hardness both with respect to the number of observations, as well as the degree of unreliability. Based on these experiments, we argue that our approach presents a significant improvement over prior work that are focused on finding a single optimal plan, and that our hypothesis exploration application can motivate the development of new planners capable of generating the top high-quality plans.

The learning of evaluation functions from game records has been widely studied in the field of computer game-playing. Conventional learning methods optimize the evaluation function parameters by using the game records of expert players in order to imitate their plays. Such conventional methods utilize objective functions to increase the agreement between the moves selected by game-playing programs and the moves in the records of actual games. The methods, however, have a problem in that increasing the agreement does not always improve the strength of a program. Indeed, it is not clear how this agreement relates to the strength of a trained program. To address this problem, this paper presents a learning method to optimize objective function parameters for strength in game-playing. The proposed method employs an evolutionary learning algorithm with the strengths (Elo ratings) of programs as their fitness scores. Experimental results show that the proposed method is effective since programs using the objective function produced by the proposed method are superior to those using conventional objective functions.