BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20240310T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231105T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250203T212519Z
UID:4DBF3C73-1859-47F0-B616-2F84DCABE3F5
DTSTART;TZID=America/New_York:20240129T180000
DTEND;TZID=America/New_York:20240129T190000
DESCRIPTION:Join the Buffalo Computer Society Chapter in welcoming Distingu
 ished Visitor\, Tulsi Thulasiram\, on Monday January 29\, at 5 PM CST/6 PM
  ET\, when he gives a virtual presentation for our new series\, Neural Net
 works of AI.\n\nTopic Summary:\n\nCryptocurrencies have emerged as an alte
 rnative financial asset in the last decade\, with their market growing exp
 onentially in recent years. The price of cryptocurrencies is highly volati
 le and is prone to rapid swings within short periods of time. This behavio
 r makes them a high-risk and high-return financial asset. The efficacy of 
 neural networks in forecasting the high frequency financial time series ha
 s become widely accepted in the research community. This work explored the
  use of Long Short-Term Memory (LSTM)\, a neural network based non-linear 
 sequence model\, to propose a novel algorithmic trading strategy for crypt
 ocurrencies. The proposed novel high frequency algorithmic trading strateg
 y built over an LSTM based short-term price forecasting is used for Bitcoi
 n and Ethereum. This simple\, yet effective trading algorithm uses the net
 work’s price forecasts to make buy and short selling decisions for crypt
 ocurrency based on certain set criteria. The proposed trading strategy giv
 es positive returns when backtested on Bitcoin hourly prices taken from ya
 hoo! finance. We also verified the effectiveness of the trading strategy f
 or Ethereum\, the second largest cryptocurrency\, based on the positive ba
 cktesting returns. As an extension to the study\, the proposed strategy is
  applied on an even higher frequency (minute by minute) Bitcoin price data
 \, and the strategy gives positive backtesting returns in this extended st
 udy. We also provide fuzzy intervals for the algorithmic return of our str
 ategy and compare those with corresponding intervals on a simple buy and h
 old strategy.\n\nCo-sponsored by: R1 Buffalo Section\n\nSpeaker(s): Dr. Tu
 lsi Thulasiram\, \n\nVirtual: https://events.vtools.ieee.org/m/399745
LOCATION:Virtual: https://events.vtools.ieee.org/m/399745
ORGANIZER:greg.koch@computer.org
SEQUENCE:24
SUMMARY:LSTM based Algorithmic Trading model for Bitcoin
URL;VALUE=URI:https://events.vtools.ieee.org/m/399745
X-ALT-DESC:Description: <br /><p>Join the Buffalo Computer Society Chapter 
 in welcoming Distinguished Visitor\, Tulsi Thulasiram\, on Monday January 
 29\, at 5 PM CST/6 PM ET\, when he gives a virtual presentation for our ne
 w series\, Neural Networks of AI.<br><br>Topic Summary:<br>&nbsp\;<br>Cryp
 tocurrencies have emerged as an alternative financial asset in the last de
 cade\, with their market growing exponentially in recent years. The price 
 of cryptocurrencies is highly volatile and is prone to rapid swings within
  short periods of time. This behavior makes them a high-risk and high-retu
 rn financial asset. The efficacy of neural networks in forecasting the&nbs
 p\; high frequency financial time series has become widely accepted in the
  research community. This work explored the use of Long Short-Term Memory 
 (LSTM)\, a neural network based non-linear sequence model\, to propose a n
 ovel algorithmic trading strategy&nbsp\; for cryptocurrencies. The propose
 d novel high frequency algorithmic&nbsp\; trading strategy built over an L
 STM based short-term&nbsp\; price forecasting is used for Bitcoin and Ethe
 reum. This simple\, yet effective trading algorithm uses the network&rsquo
 \;s price forecasts to make buy and short selling decisions for cryptocurr
 ency based on certain set criteria. The proposed trading strategy gives po
 sitive returns when backtested on Bitcoin hourly prices taken from yahoo! 
 finance. We also verified the effectiveness of the trading strategy for Et
 hereum\, the second largest cryptocurrency\,&nbsp\; based on the positive 
 backtesting returns. As an extension to the study\, the proposed strategy 
 is applied on an even higher frequency (minute by minute) Bitcoin price da
 ta\, and the strategy&nbsp\; gives positive backtesting returns in this ex
 tended study. We also provide fuzzy intervals for the algorithmic return o
 f our strategy and compare those with corresponding intervals on a simple 
 buy and hold strategy.</p>
END:VEVENT
END:VCALENDAR