James Franklin

A text-based decision support system for financial sequence prediction

Although most quantitative financial data are analyzed using traditional statistical, artificial intelligence or data mining techniques, the abundance of online electronic financial news articles has opened up new possibilities for intelligent systems that can extract and organize relevant knowledge automatically in a usable format. Most information extraction systems require a hand-built dictionary of templates and thus need continual modification to accommodate new patterns that are observed in the text. In this research, we propose a novel text-based decision support system (DSS) that (i) extracts event sequences from shallow text patterns, and (ii) predicts the likelihood of the occurrence of events using a classifier-based inference engine. The prediction relies on two major, but complementary, feature sets: adjacent events and a set of information-theoretic functions. In contrast to other approaches, the proposed text-based DSS gives explanatory hypotheses about its predictions from a coalition of intimations learned from the inference engine, while preserving robustness and without indulging in formalism. We investigate more than 2000 financial reports with 28,000 sentences. Experiments show that the prediction accuracy of our model outperforms similar statistical models by 7% for the seen data while significantly improving the prediction accuracy for the unseen data. Further comparisons substantiate the experimental findings.

Explanation in Mathematics

There is a philosophical debate on explanation in science, and a philosophical debate on explanation in mathematics. They have proceeded largely independently of each other. For example, the Stanford Encyclopedia of Philosophy articles on ‘Scientific explanation’1 and ‘Explanation in mathematics’2 barely mention any common issues and have only three items in common in their extensive bibliographies. That is strange, since prima facie explanation works much the same way in mathematics and in science. An account of scientific explanation is incomplete if it does not cover explanation in mathematics (or at least include some reasoning on why the mathematical case is different).

Symbolic connectionism in natural language disambiguation

Natural language understanding involves the simultaneous consideration of a large number of different sources of information. Traditional methods employed in language analysis have focused on developing powerful formalisms to represent syntactic or semantic structures along with rules for transforming language into these formalisms. However, they make use of only small subsets of knowledge. This article will describe how to use the whole range of information through a neurosymbolic architecture which is a hybridization of a symbolic network and subsymbol vectors generated from a connectionist network. Besides initializing the symbolic network with prior knowledge, the subsymbol vectors are used to enhance the systems capability in disambiguation and provide flexibility in sentence understanding. The model captures a diversity of information including word associations, syntactic restrictions, case-role expectations, semantic rules and context. It attains highly interactive processing by representing knowledge in an associative network on which actual semantic inferences are performed. An integrated use of previously analyzed sentences in understanding is another important feature of our model. The model dynamically selects one hypothesis among multiple hypotheses. This notion is supported by three simulations which show the degree of disambiguation relies both on the amount of linguistic rules and the semantic-associative information available to support the inference processes in natural language understanding. Unlike many similar systems, our hybrid system is more sophisticated in tackling language disambiguation problems by using linguistic clues from disparate sources as well as modeling context effects into the sentence analysis. It is potentially more powerful than any systems relying on one processing paradigm.

Non-Deductive Logic in Mathematics

If mathematical realism - whether Platonist or Aristotelian - is true, then mathematics is a scientific study of a world ‘out there’. In that case, in addition to methods special to mathematics such as proof, there ought to be a role for ordinary scientific methods such as experiment, conjecture and the confirmation of theories by observations. Those methods should work in mathematics just as well as in science. Mathematics has extra and more certain methods of its own, but that should not prevent ordinary scientific methods from working.

Modeling extreme risks in ecology.

Extreme risks in ecology are typified by circumstances in which data are sporadic or unavailable, understanding is poor, and decisions are urgently needed. Expert judgments are pervasive and disagreements among experts are commonplace. We outline approaches to evaluating extreme risks in ecology that rely on stochastic simulation, with a particular focus on methods to evaluate the likelihood of extinction and quasi-extinction of threatened species, and the likelihood of establishment and spread of invasive pests. We evaluate the importance of assumptions in these assessments and the potential of some new approaches to account for these uncertainties, including hierarchical estimation procedures and generalized extreme value distributions. We conclude by examining the treatment of consequences in extreme risk analysis in ecology and how expert judgment may better be harnessed to evaluate extreme risks.

The formal sciences discover the philosophers' stone

Aristotelians deplore the narrow range of examples chosen for discussion in traditional philosophy of mathematics. The traditional diet – numbers, sets, infinite cardinals, axioms, theorems of formal logic – is far from typical of what mathematicians do. It has led to intellectual anorexia, by depriving the philosophy of mathematics of the nourishment it could and should receive from the expansive world of mathematics of the last hundred years. Philosophers have almost completely ignored not only the broad range of pure and applied mathematics and statistics, but a whole suite of ‘formal’ or ‘mathematical’ sciences that have appeared only in the last eighty years. I give here a few brief examples to indicate why these developments are of philosophical interest to those pursuing realist views of mathematics. Of special significance is that they contain many examples of necessities about the real world.

Diagrammatic Reasoning and Modelling in the Imagination: The Secret Weapons of the Scientific Revolution

Tartaglia’s Italian Euclid of 1543 is geometry in the narrow sense. But the big two books of 1543, Copernicus’ De revolutionibus and Vesalius’ De humani corporis fabrica are also geometry, if a slightly wider sense of the term is allowed. Though Copernicus writes on physics, he does not speak of forces, energies, masses or the like: there are only the appearances of the heavens from certain points of view. Though Vesalius is biology, there is little physiology, or mechanical analogy, or discussion of causes: the emphasis is on how parts of the body look from suitable points of view. But the three books share more than just pictures, and it is this extra element that is the focus of this article. Euclid’s Elements is not a picture book of shapes. The point of Euclid is to reason about the diagrams, and expose the necessary interrelations of the spatial parts. So it is with Copernicus and Vesalius. The text of Copernicus is an exercise in reasoning about which geometrical scheme will best fit the sequences of spatial points recorded in the astronomical tables. Vesalius uses the best of the discoveries of artists to make easy for the reader inference about how the systems of the body look in isolation, and in relation to one another. The difference between a Vesalian diagram and a photograph is exactly that the former allows one to work out structural facts which are almost invisible in the photograph.

Two caricatures, I: Pascal's wager

Pascal’s wager and Leibniz’s theory that this is the best of a ll possible worlds are latecomers in the Faith-and-Reason tradition. They have remained interlopers; they have never been taken as seriously as the older arguments for the existence of God and other themes related to faith and reason. They have, indeed, aroused a common reaction in the hearts of all rightthinking non-believers: indignation. And the ire of the irr eligious in this matter has been exceeded only by the me-tooism of the faithful, as they run for cover at the suggestion that there may be any points of agreement between themselves and Pascal or Leibniz. Still, indignation is beside the point when it comes to evaluating any argument. Pascal and Leibniz discovered certain chains of reasoning. If they have any logical force, that force is not taken away by the fact that the arguments are inconvenient for someone’s moral views. Given th e tendency of indignation to shoot first and ask questions later, it is mor e likely that it will obscure clear thinking about the arguments, by twisting one’s perception of what the arguments actually say. That is exactly what has happened. What Pascal said.You have to choose whether to accept religion. Think of it as a coin toss, where you don’t know the outcome. In this case, i f you lose ‐ there’s no God ‐ you have not lost much. But if you win, there is a n infinite payoff. So, you should go to Mass, and pray for faith. 1

The Ancient Legal Sources of Seventeenth-Century Probability

The Scientific Revolution of the seventeenth century might almost equally well be called the Mathematical Revolution. Experimentation was important, but even there one of the advances was the systemic extension of measurement, to such quantities as time, speed, pressure and probability. The initial reduction of data to numerical form enabled the discovery of patterns in them like the laws of motion, and the creation of mathematical theories of continuity (the calculus) and of probability.

Randomness and the justification of induction

In 1947 Donald Cary Williams claimed in The Ground of Induction to have solved the Humean problem of induction, by means of an adaptation of reasoning first advanced by Bernoulli in 1713. Later on David Stove defended and improved upon Williams’ argument in The Rationality of Induction (1986). We call this proposed solution of induction the ‘Williams-Stove sampling thesis’. There has been no lack of objections raised to the sampling thesis, and it has not been widely accepted. In our opinion, though, none of these objections has the slightest force, and, moreover, the sampling thesis is undoubtedly true. What we will argue in this paper is that one particular objection that has been raised on numerous occasions is misguided. This concerns the randomness of the sample on which the inductive extrapolation is based.