Algorithmic Trading

"Networks are mathematically directed (in practical applications also undirected) graphs and a graph is a one-dimensional abstract complex, i.e., a topological space. Network theory focuses on various topological structures and properties, dynamic properties, and functionality-topology relationship, etc. There are some common mathematical foundations, theories and methodology for network analysis, in which graph theory, statistics, and operational research, etc., are the fundamental sciences of network analysis. Various emerging biological networks, at both micro- and macro- levels, will provide numerous sources for the development of general network theory and methodology and also facilitate the development of theory and methodology of biological networks.

Biological network analysis is a fast moving science. Many core scientific issues, for example, ecological structure, co-evolution, co-extinction and biodiversity conservation in ecology, and cancer development and metabolic regulation in health science, etc., are expected to be addressed by network approaches and network analysis. Network analysis is becoming the core methodology to treat complex biological systems. As the fast development of this area, more and more papers on biological networks are published.

At present explosive numbers of quality papers on biological networks are being published each year. The initiation of the journal, Network Biology, will provide a public and unified platform for the publication of these studies. From this integrated and unique journal, researchers, university teachers and students will thoroughly have an in-depth and complete insight on knowledge, methodology and recent advances of biological networks.

In the view of system dynamics, biological networks are always self-organized systems with emergent, autonomous and adaptive properties. Their dynamics can be represented by agent-based modeling, individual-based modeling and some other methodologies like neural network modeling. Therefore, agent-based modeling, individual-based modeling, self-organization of biological systems, and neural network modeling, etc., fall into the aims and scope of the journal, Network Biology.

The NETWORK BIOLOGY (ISSN 2220-8879) is an open access, peer-reviewed online journal that considers scientific articles in all different areas of network biology. It is the transactions of the International Society of Network Biology.It dedicates to the latest advances in network biology. The goal of this journal is to keep a record of the state-of-the-art research and promote the research work in these fast moving areas. The topics to be covered by Network Biology include, but are not limited to:

•Theories, algorithms and programs of network analysis
•Innovations and applications of biological networks
•Dynamics, optimization and control of biological networks
•Ecological networks, food webs and natural equilibrium
•Co-evolution, co-extinction, biodiversity conservation
•Metabolic networks, protein-protein interaction networks, biochemical reaction networks, gene networks, transcriptional regulatory networks, cell cycle networks, phylogenetic networks, network motifs
•Physiological networks
•Network regulation of metabolic processes, human diseases and ecological systems
•Social networks, epidemiological networks
•System complexity, self-organized systems, emergence of biological systems, agent-based modeling, individual-based modeling, neural network modeling, and other network-based modeling, etc.
We are also interested in short communications that clearly address a specific issue or completely present a new ecological network, food web, or metabolic or gene network, etc.

Authors can submit their works to the email box of this journal, [email protected]. All manuscripts submitted to this journal must be previously unpublished and may not be considered for publication elsewhere at any time during review period of this journal. Authors are asked to read Author Guidelines before submitting manuscripts.

In addition to free submissions from authors around the world, special issues are also accepted. The organizer of a special issue can collect submissions (yielded from a research project, a research group, etc.) on a specific research topic, or submissions of a scientific conference for publication of special issue.

Network Biology 
ISSN 2220-8879
URL: http://www.iaees.org/publications/journals/nb/online-version.asp
RSS feed: http://www.iaees.org/publications/journals/nb/rss.xml
E-mail: [email protected]
Editor-in-Chief: WenJun Zhang"

L’obiettivo principale dell’elaborato è quello di fornire uno strumento di supporto alla decisione dell’investitore in merito all'acquisto o alla vendita di titoli finanziari. A partire da una timeserie con le oscillazioni storiche di prezzo di un titolo, si vogliono trovare degli algoritmi in grado di stabilire i momenti futuri più favorevoli per acquistarlo o venderlo.
Più in particolare, il nostro punto di partenza sarà un dataset di pattern
(successione di prezzi che d`a luogo a particolari configurazioni grafiche), riconosciuti in modo deterministico, che dovrebbero dare un’indicazione sul trend dei prossimi giorni. Questi pattern sono molto utilizzati dai traders e probabilmente celano al loro interno informazioni rilevanti. Tuttavia, adottare una strategia di trading solo ed esclusivamente seguendo segnali di tipo grafico può essere alquanto rischioso; difatti l’indicazione associata ad un pattern noto si verifica nelle situazioni reali solo con soglie di probabilità leggermente superiori al 60%.
Si tratta di un valore decisamente basso per più ragioni: anzitutto si tenga presente che ogni volta in cui si entra o esce da una posizione (ossia si aggiunge e poi si liquida un titolo dal portafoglio) vengono pagate delle spese di commissione le quali ammontano a circa 0,4% del controvalore. Inoltre, poiché i segnali derivanti dall'analisi grafica hanno senso solo se valutati in un’ottica di breve/brevissimo termine, le commissioni risultano fortemente influenti perché i trade fatti con analisi di questo tipo danno luogo a profitti su scostamenti di prezzo al di sotto dell' 1%. In fine, non è sempre possibile acquistare o vendere un titolo nel momento in cui scatta un segnale grafico.
Per sopperire a tutte queste criticità si rende perciò necessario aumentare le probabilità di successo dei nostri segnali. Per fare ciò l’elaborato si propone di utilizzare una serie di tecniche di machine learning supervised per selezionare - tra i pattern riconosciuti in modo deterministico - quelli che hanno più probabilità d’essere corretti.
L'analisi è stata svolta con il software R sia per la numerosità dei packages attinenti alla statistica e al machine learning, sia perché si tratta di un applicativo open-source.

In information societies, operations, decisions and choices previously left to humans are increasingly delegated to algorithms, which may advise, if not decide, about how data should be interpreted and what actions should be taken as a result. More and more often, algorithms mediate social processes, business transactions, governmental decisions, and how we perceive, understand, and interact among ourselves and with the environment. Gaps between the design and operation of algorithms and our understanding of their ethical implications can have severe consequences affecting individuals as well as groups and whole societies. This paper makes three contributions to clarify the ethical importance of algorithmic mediation. It provides a prescriptive map to organise the debate. It reviews the current discussion of ethical aspects of algorithms. And it assesses the available literature in order to identify areas requiring further work to develop the ethics of algorithms.

The paper presents a model for forecasting association football scores. The model uses a Weibull inter-arrival-times-based count process and a copula to produce a bivariate distribution of the numbers of goals scored by the home and away teams in a match. We test it against a variety of alternatives, including the simpler Poisson distribution-based model and an independent version of our model. The out-of-sample performance of our methodology is illustrated using, first, calibration curves, then a Kelly-type betting strategy that is applied to the pre-match win/draw/loss market and to the over–under 2.5 goals market. The new model provides an improved fit to the data relative to previous models, and results in positive returns to betting.