Modeling Financial Time Series with Artificial Neural Networks

Financial time series convey the decisions and actions of a population of human actors over time. Econometric and regressive models have been developed in the past decades for analyzing these time series. More recently, biologically inspired artificial neural network models have been shown to overcome some of the main challenges of traditional techniques by better exploiting the non-linear, non-stationary, and oscillatory nature of noisy, chaotic human interactions. This review paper explores the options, benefits, and weaknesses of the various forms of artificial neural networks as compared with regression techniques in the field of financial time series analysis.

A distributed architecture for the monitoring and analysis of time series data

It is estimated that the quantity of digital data being transferred, processed or stored at any one time currently stands at 4.4 zettabytes (4.4 × 2 70 bytes) and this figure is expected to have grown by a factor of 10 to 44 zettabytes by 2020. Exploiting this data is, and will remain, a significant challenge. At present there is the capacity to store 33% of digital data in existence at any one time; by 2020 this capacity is expected to fall to 15%. These statistics suggest that, in the era of Big Data, the identification of important, exploitable data will need to be done in a timely manner. Systems for the monitoring and analysis of data, e.g. stock markets, smart grids and sensor networks, can be made up of massive numbers of individual components. These components can be geographically distributed yet may interact with one another via continuous data streams, which in turn may affect the state of the sender or receiver. This introduces a dynamic causality, which further complicates the overall system by introducing a temporal constraint that is difficult to accommodate. Practical approaches to realising the system described above have led to a multiplicity of analysis techniques, each of which concentrates on specific characteristics of the system being analysed and treats these characteristics as the dominant component affecting the results being sought. The multiplicity of analysis techniques introduces another layer of heterogeneity, that is heterogeneity of approach, partitioning the field to the extent that results from one domain are difficult to exploit in another. The question is asked can a generic solution for the monitoring and analysis of data that: accommodates temporal constraints; bridges the gap between expert knowledge and raw data; and enables data to be effectively interpreted and exploited in a transparent manner, be identified? The approach proposed in this dissertation acquires, analyses and processes data in a manner that is free of the constraints of any particular analysis technique, while at the same time facilitating these techniques where appropriate. Constraints are applied by defining a workflow based on the production, interpretation and consumption of data. This supports the application of different analysis techniques on the same raw data without the danger of incorporating hidden bias that may exist. To illustrate and to realise this approach a software platform has been created that allows for the transparent analysis of data, combining analysis techniques with a maintainable record of provenance so that independent third party analysis can be applied to verify any derived conclusions. In order to demonstrate these concepts, a complex real world example involving the near real-time capturing and analysis of neurophysiological data from a neonatal intensive care unit (NICU) was chosen. A system was engineered to gather raw data, analyse that data using different analysis techniques, uncover information, incorporate that information into the system and curate the evolution of the discovered knowledge. The application domain was chosen for three reasons: firstly because it is complex and no comprehensive solution exists; secondly, it requires tight interaction with domain experts, thus requiring the handling of subjective knowledge and inference; and thirdly, given the dearth of neurophysiologists, there is a real world need to provide a solution for this domain

Empirical Evidence of Conditional Heteroskedasticity in Vietnam’s Stock Returns Time Series

This paper confirms presence of GARCH(1,1) effect on stock return time series of Vietnam’s newborn stock market. We performed tests on four different time series, namely market returns (VN-Index), and return series of the first four individual stocks listed on the Vietnamese exchange (the Ho Chi Minh City Securities Trading Center) since August 2000. The results have been quite relevant to previously reported empirical studies on different markets.

Comparison of pattern detection methods in microarray time series of the segmentation clock.

While genome-wide gene expression data are generated at an increasing rate, the repertoire of approaches for pattern discovery in these data is still limited. Identifying subtle patterns of interest in large amounts of data (tens of thousands of profiles) associated with a certain level of noise remains a challenge. A microarray time series was recently generated to study the transcriptional program of the mouse segmentation clock, a biological oscillator associated with the periodic formation of the segments of the body axis. A method related to Fourier analysis, the Lomb-Scargle periodogram, was used to detect periodic profiles in the dataset, leading to the identification of a novel set of cyclic genes associated with the segmentation clock. Here, we applied to the same microarray time series dataset four distinct mathematical methods to identify significant patterns in gene expression profiles. These methods are called: Phase consistency, Address reduction, Cyclohedron test and Stable persistence, and are based on different conceptual frameworks that are either hypothesis- or data-driven. Some of the methods, unlike Fourier transforms, are not dependent on the assumption of periodicity of the pattern of interest. Remarkably, these methods identified blindly the expression profiles of known cyclic genes as the most significant patterns in the dataset. Many candidate genes predicted by more than one approach appeared to be true positive cyclic genes and will be of particular interest for future research. In addition, these methods predicted novel candidate cyclic genes that were consistent with previous biological knowledge and experimental validation in mouse embryos. Our results demonstrate the utility of these novel pattern detection strategies, notably for detection of periodic profiles, and suggest that combining several distinct mathematical approaches to analyze microarray datasets is a valuable strategy for identifying genes that exhibit novel, interesting transcriptional patterns.

Continuity and Change on an Urban Houselot: Archaeological Excavation at the 22 West Street Backlot (18AP51) of the Annapolis National Historic District, Anne Arundel County, Maryland

Intensive archaeological investigation was undertaken on an urban backlot in Annapolis, Maryland. Fieldwork was conducted on behalf of Historic Annapolis Foundation for the property's owners, King and Cornwall, Inc. Supplemental documentary research, an evaluation of existing conditions on the property, and below-ground excavation of a 35 X 70 ft. urban backlot were conducted. While the project was not a Section 106 compliance effort, the field methods and rationale for the site's investigation are comparable to those of standard Phase II site evaluations. Historical documentation attested to the fact that the 22 West Street Backlot, located along the western most edge of the Historic District of Annapolis, Maryland, had seen development and occupation since the first quarter of the eighteenth century. A substantial brick structure was known to have occupied the property in a series of altered forms for much of that period. This structure served a variety of purposes over time: a private residence in the eighteenth century, a boarding house in the nineteenth century (known as the National Hotel), a duplex in the early twentieth century, half of which remained in use until the structure was entirely razed in the 1970s after destruction by fire. Recovery and analysis of site formation processes (i.e., both cultural and natural transformations of the buried remains) indicated that sections of the site were disturbed to a depth of six feet. In contrast to what initially seemed a poor prognosis for site integrity, other areas of the backlot revealed numerous intact historical features and deposits. Structural remains from the dwelling and its associated outbuildings, additions, and attendant trash deposits were recovered. What was initiated as a program of limited testing evolved into a larger-scale undertaking that made use of largely hand-excavated units in conjunction with machine-assisted stripping of areas demonstrated to contain from four to six-foot deep sterile layers of fill. The current investigations provided a window into a portion of the city and period in its history not documented archaeologically. Moreover, this project provided valuable insight into the archaeology of the homelot within a lightly industrialized, urban context. Evidence was recovered of shifts in the layout and arrangement of the houselot as well as changing relations between individuals and the workplace--all within an urban context--an issue defined elsewhere in the archaeological literature as a significant one. No further investigations are recommended for the site, however, further analysis and interpretation of materials recovered are ongoing. In the event that the site were to undergo development, monitoring of any construction activity is recommended.

BioHackathon series in 2011 and 2012: penetration of ontology and linked data in life science domains.

The application of semantic technologies to the integration of biological data and the interoperability of bioinformatics analysis and visualization tools has been the common theme of a series of annual BioHackathons hosted in Japan for the past five years. Here we provide a review of the activities and outcomes from the BioHackathons held in 2011 in Kyoto and 2012 in Toyama. In order to efficiently implement semantic technologies in the life sciences, participants formed various sub-groups and worked on the following topics: Resource Description Framework (RDF) models for specific domains, text mining of the literature, ontology development, essential metadata for biological databases, platforms to enable efficient Semantic Web technology development and interoperability, and the development of applications for Semantic Web data. In this review, we briefly introduce the themes covered by these sub-groups. The observations made, conclusions drawn, and software development projects that emerged from these activities are discussed.

A Dynamic Directional Model for Effective Brain Connectivity using Electrocorticographic (ECoG) Time Series.

We introduce a dynamic directional model (DDM) for studying brain effective connectivity based on intracranial electrocorticographic (ECoG) time series. The DDM consists of two parts: a set of differential equations describing neuronal activity of brain components (state equations), and observation equations linking the underlying neuronal states to observed data. When applied to functional MRI or EEG data, DDMs usually have complex formulations and thus can accommodate only a few regions, due to limitations in spatial resolution and/or temporal resolution of these imaging modalities. In contrast, we formulate our model in the context of ECoG data. The combined high temporal and spatial resolution of ECoG data result in a much simpler DDM, allowing investigation of complex connections between many regions. To identify functionally segregated sub-networks, a form of biologically economical brain networks, we propose the Potts model for the DDM parameters. The neuronal states of brain components are represented by cubic spline bases and the parameters are estimated by minimizing a log-likelihood criterion that combines the state and observation equations. The Potts model is converted to the Potts penalty in the penalized regression approach to achieve sparsity in parameter estimation, for which a fast iterative algorithm is developed. The methods are applied to an auditory ECoG dataset.

Mid-term results and factors affecting outcome of a metal-backed unicompartmental knee design: a case series.

BACKGROUND: Controversies exist regarding the indications for unicompartmental knee arthroplasty. The objective of this study is to report the mid-term results and examine predictors of failure in a metal-backed unicompartmental knee arthroplasty design. METHODS: At a mean follow-up of 60 months, 80 medial unicompartmental knee arthroplasties (68 patients) were evaluated. Implant survivorship was analyzed using Kaplan-Meier method. The Knee Society objective and functional scores and radiographic characteristics were compared before surgery and at final follow-up. A Cox proportional hazard model was used to examine the association of patient's age, gender, obesity (body mass index > 30 kg/m2), diagnosis, Knee Society scores and patella arthrosis with failure. RESULTS: There were 9 failures during the follow up. The mean Knee Society objective and functional scores were respectively 49 and 48 points preoperatively and 95 and 92 points postoperatively. The survival rate was 92% at 5 years and 84% at 10 years. The mean age was younger in the failure group than the non-failure group (p < 0.01). However, none of the factors assessed was independently associated with failure based on the results from the Cox proportional hazard model. CONCLUSION: Gender, pre-operative diagnosis, preoperative objective and functional scores and patellar osteophytes were not independent predictors of failure of unicompartmental knee implants, although high body mass index trended toward significance. The findings suggest that the standard criteria for UKA may be expanded without compromising the outcomes, although caution may be warranted in patients with very high body mass index pending additional data to confirm our results. LEVEL OF EVIDENCE: IV.

Botulinum toxin type A injections for the management of muscle tightness following total hip arthroplasty: a case series.

BACKGROUND: Development of hip adductor, tensor fascia lata, and rectus femoris muscle contractures following total hip arthroplasties are quite common, with some patients failing to improve despite treatment with a variety of non-operative modalities. The purpose of the present study was to describe the use of and patient outcomes of botulinum toxin injections as an adjunctive treatment for muscle tightness following total hip arthroplasty. METHODS: Ten patients (14 hips) who had hip adductor, abductor, and/or flexor muscle contractures following total arthroplasty and had been refractory to physical therapeutic efforts were treated with injection of botulinum toxin A. Eight limbs received injections into the adductor muscle, 8 limbs received injections into the tensor fascia lata muscle, and 2 limbs received injection into the rectus femoris muscle, followed by intensive physical therapy for 6 weeks. RESULTS: At a mean final follow-up of 20 months, all 14 hips had increased range in the affected arc of motion, with a mean improvement of 23 degrees (range, 10 to 45 degrees). Additionally all hips had an improvement in hip scores, with a significant increase in mean score from 74 points (range, 57 to 91 points) prior to injection to a mean of 96 points (range, 93 to 98) at final follow-up. There were no serious treatment-related adverse events. CONCLUSION: Botulinum toxin A injections combined with intensive physical therapy may be considered as a potential treatment modality, especially in difficult cases of muscle tightness that are refractory to standard therapy.

Nasopharyngeal Masses Arising from Embryologic Remnants of the Clivus: A Case Series.

Objectives This study aims to (1) discuss rare nasopharyngeal masses originating from embryologic remnants of the clivus, and (2) discuss the embryology of the clivus and understand its importance in the diagnosis and treatment of these masses. Design and Participants This is a case series of three patients. We discuss the clinical and imaging characteristics of infrasellar craniopharyngioma, intranasal extraosseous chordoma, and canalis basilaris medianus. Results Case 1: A 16-year-old male patient with a history of craniopharyngioma resection, who presented with nasal obstruction. A nasopharyngeal cystic mass was noted to be communicating with a patent craniopharyngeal canal. Histology revealed adamantinomatous craniopharyngioma. Case 2: A 43-year-old male patient who presented with nasal obstruction and headache. Computed tomography (CT) and magnetic resonance imaging revealed an enhancing polypoid mass in the posterior nasal cavity abutting the clivus. Histopathology revealed chondroid chordoma. Case 3: A 4-year-old female patient with a recurrent nasopharyngeal polyp. CT cisternogram showed that this mass may have risen from a bony defect of the middle clivus suggestive of canalis basilaris medianus. Conclusions Understanding the embryology of the clivus is crucial when considering the differential diagnosis of a nasopharyngeal mass. Identification of characteristic findings on imaging is critical in the diagnosis and treatment of these lesions.

Algae-Based Purification of Landfill Biogas Using a CO2 Removal System and Helical Photobioreactor in Series

Biogas is a mixture of methane and other gases. In its crude state, it contains carbon dioxide (CO2) that reduces its energy efficiency and hydrogen sulfide (H2S) that is toxic and highly corrosive. Because chemical methods of removal are expensive and environmentally hazardous, this project investigated an algal-based system to remove CO2 from biogas. An anaerobic digester was used to mimic landfill biogas. Iron oxide and an alkaline spray were used to remove H2S and CO2 respectively. The CO2-laden alkali solution was added to a helical photobioreactor where the algae metabolized the dissolved CO2 to generate algal biomass. Although technical issues prevented testing of the complete system for functionality, cost analysis was completed and showed that the system, in its current state, is not economically feasible. However, modifications may reduce operation costs.

Sobre la finitud de las series de potencias infinitas de tipo geometrico-polinomiales

Una investigación que inicie a mediados del ano 2004, para tratar de encontrar como pudieron hacer los matemáticos de fines del siglo XVII, para encontrar la suma de algunas series de potencias infinitas.

Some models for discretized series of events

A discretized series of events is a binary time series that indicates whether or not events of a point process in the line occur in successive intervals. Such data are common in environmental applications. We describe a class of models for them, based on an unobserved continuous-time discrete-state Markov process, which determines the rate of a doubly stochastic Poisson process, from which the binary time series is constructed by discretization. We discuss likelihood inference for these processes and their second-order properties and extend them to multiple series. An application involves modeling the times of exposures to air pollution at a number of receptors in Western Europe.

Single machine scheduling and due date assignment under series-parallel precedence constraints

We consider a single machine due date assignment and scheduling problem of minimizing holding costs with no tardy jobs tinder series parallel and somewhat wider class of precedence constraints as well as the properties of series-parallel graphs.

An ontological characterization of time-series and state-sequences for data mining

Time-series and sequences are important patterns in data mining. Based on an ontology of time-elements, this paper presents a formal characterization of time-series and state-sequences, where a state denotes a collection of data whose validation is dependent on time. While a time-series is formalized as a vector of time-elements temporally ordered one after another, a state-sequence is denoted as a list of states correspondingly ordered by a time-series. In general, a time-series and a state-sequence can be incomplete in various ways. This leads to the distinction between complete and incomplete time-series, and between complete and incomplete state-sequences, which allows the expression of both absolute and relative temporal knowledge in data mining.