System for foreign exchange trading using genetic algorithms and reinforcement learning

Foreign exchange trading has emerged recently as a significant activity in many countries. As with most forms of trading, the activity is influenced by many random parameters so that the creation of a system that effectively emulates the trading process will be very helpful. A major issue for traders in the deregulated Foreign Exchange Market is when to sell and when to buy a particular currency in order to maximize profit. This paper presents novel trading strategies based on the machine learning methods of genetic algorithms and reinforcement learning.

'Seeing the market': Technical analysis in trading styles

Whilst financial markets are not strangers to academic and professional scrutiny, they still remain epistemologically contested. For individuals trying to profit by trading shares, this uncertainty is manifested in the varying trading styles which they are able to utilize. This paper examines one trading style commonly used by non-professional share traders-technical analysis. Using research data obtained from individuals who identify themselves as technical analysts, this paper seeks to explain the ways in which individuals understand and use the technique in an attempt to make trading profits. In particular, four distinct subcategories or ideal types of technical analysis can be identified, each providing an alternative perceptual form for participating in financial markets. Each of these types relies upon a particular method for seeing the market, these visualization techniques highlighting the existence of forms of professional vision (as originally identified by Goodwin (1994)) in the way the trading styles are comprehended and acted upon.

Opioids and NMDA receptors: Neuro-excitation and abnormal pain behaviours

In the clinical setting, chronic administration of high doses of systemic morphine may result in neuro-excitatory behaviours such as myoclonus and allodynia in some patients. Additionally, high doses of m-opioid agonists such as morphine administered chronically by the intrathecal route in both rats and humans, as well as DAMGO in rats, have been reported to produce neuro-excitatory behaviours. However, more recently, it has begun to be appreciated that even at normal analgesic doses, opioids such as morphine are capable not only of activating pain inhibitory systems (analgesia/antinociception), but they also activate pain facilitatory systems such that post-opioid allodynia/hyperalgesia may be evident after cessation of opioid treatment. Whilst it is well documented that opioid receptors mediate the inhibitory effects of opioid analgesics, the excitatory and pro-nociceptive effects of opioids appear to involve indirect activation of N-methyl-D-aspartate (NMDA) receptors, such that the extent of pain relief produced may be the net effect of these two opposing actions. Apart from the NMDA-nitric oxide (NO) pro-nociceptive signaling cascade, considerable evidence also implicates dynorphin A as well as the endogenous anti-opioid peptides cholecystokinin (CCK), neuropeptide FF (NPFF) and orphanin FQ/nociceptin, in mediating opioid-induced neuro-excitation and abnormal pain behaviours. Apart from the neuro-excitatory effects that may be produced by the parent opioid, systemic administration of some opioid analgesics such as morphine and hydromorphone in rats and humans results in their rapid conversion to 3-glucuronide metabolites that also contribute significantly to the neuro-excitatory and abnormal pain behaviours produced