BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Pacific BEGIN:DAYLIGHT DTSTART:20240310T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20241103T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20240729T205000Z UID:A1C757F0-D1A1-461C-B153-5D091505FADF DTSTART;TZID=US/Pacific:20240729T093000 DTEND;TZID=US/Pacific:20240729T123000 DESCRIPTION:The increase in popularity of machine learning models and algor ithms has brought up methods for increasing the efficiency of processes in various industries and new use cases. From corporations to individuals\, machine learning is applicable in a wide range of settings. One such appli cation is using machine learning models for stock price forecasting. This area is often studied. However\, it still needs to solve problems due to t he high complexity and volatility that technical factors and sentiment-ana lysis models try to capture. Based on this premise\, we suggested building up our previous experience building short-term forecasting models using m achine learning models. The research project aims to develop practical alg orithmic trading algorithms based on accurate short-term forecasts for fin ancial time series using machine learning models. The project focuses on t hese research activities:\n\n- Building a database containing the targeted financial and other time series is valuable input to the machine learning models. This streamlines the process of acquiring financial data required for training the machine learning model by adding a web UI for configurin g data collection automation and extracting required data.\n- A short-term forecasting model based on machine learning is developed using the variou s time-series data from the data warehouse. Machine learning algorithms su ch as neural networks\, random forecasts\, support vector regression\, XGB oost\, and long short-term memory (LSTM) are evaluated with several perfor mance criteria to identify the most accurate model from a short-term tradi ng perspective. After the performance analysis based on several metrics\, XGBoost was chosen for further development.\n\nWe will demonstrate how to evaluate the quality of the collected data\, the metrics of the machine le arning model’s prediction\, and their integration.\n\nCo-sponsored by: I EEE Okanagan College Student Branch\n\nSpeaker(s): Albert Wong\, Gaétan H ains\, Ajitesh Parihar \n\nAgenda: \n1. Welcome from the IEEE Okanagan Sub section\, IEEE Okanagan College Student Branch and Computer Science Depart ment: Dr. Youry Khmelevsky\, Chair (9:30 am – 9:35 am)\n2. Invited speak er from the University of Paris East Creteil: Dr. Gaétan Hains (9:35 am – 10:15 am)\n3. Invited speakers from Langara College: Dr. Albert Wong & Andres C. Viloria Garcia (10:15 am – 11:00 am)\n      Machi ne Learning algorithms for stock price forecasting\n      Mode l building process and methodology\n      Normalization and pe rformance evaluation\n      Iterations and results\n4. Coffee Break (11:00 am - 11:15 am)\n5. Student research project presentation and demonstration (11:15 am - 12:30 pm)\n      Database design\n       Data collection process automation\n      Ex traction\, Transformation and Loading Process\n      UI develo pment for data configurations and extraction\n      Integratio n prototype using Jupyter notebooks\n\nWe will demonstrate how to evaluate the quality of the collected data\, the metrics of the machine learning m odel’s prediction\, and their integration.\n\nRoom: 310\, Bldg: E\, 1000 KLO Rd.\, Kelowna\, British Columbia\, Canada\, V1Y 4X8\, Virtual: https: //events.vtools.ieee.org/m/428090 LOCATION:Room: 310\, Bldg: E\, 1000 KLO Rd.\, Kelowna\, British Columbia\, Canada\, V1Y 4X8\, Virtual: https://events.vtools.ieee.org/m/428090 ORGANIZER:youry@ieee.org SEQUENCE:18 SUMMARY:Algorithmic Trading and Short-term Forecast for Financial Time Seri es with Machine Learning Models Implementation and Testing Workshop URL;VALUE=URI:https://events.vtools.ieee.org/m/428090 X-ALT-DESC:Description: <br /><p>The increase in popularity of machine lear ning models and algorithms has brought up methods for increasing the effic iency of processes in various industries and new use cases. From corporati ons to individuals\, machine learning is applicable in a wide range of set tings. One such application is using machine learning models for stock pri ce forecasting. This area is often studied. However\, it still needs to so lve problems due to the high complexity and volatility that technical fact ors and sentiment-analysis models try to capture. Based on this premise\, we suggested building up our previous experience building short-term forec asting models using machine learning models. The research project aims to develop practical algorithmic trading algorithms based on accurate short-t erm forecasts for financial time series using machine learning models. The project focuses on these research activities:</p>\n<ol>\n<li aria-level=" 1">Building a database containing the targeted financial and other time se ries is valuable input to the machine learning models. This streamlines th e process of acquiring financial data required for training the machine le arning model by adding a web UI for configuring data collection automation and extracting required data.</li>\n<li aria-level="1">A short-term forec asting model based on machine learning is developed using the various time -series data from the data warehouse. Machine learning algorithms such as neural networks\, random forecasts\, support vector regression\, XGBoost\, and long short-term memory (LSTM) are evaluated with several performance criteria to identify the most accurate model from a short-term trading per spective. After the performance analysis based on several metrics\, XGBoos t was chosen for further development.</li>\n</ol>\n<p>We will demonstrate how to evaluate the quality of the collected data\, the metrics of the mac hine learning model&rsquo\;s prediction\, and their integration.<strong>&n bsp\;</strong></p><br /><br />Agenda: <br /><p>1. Welcome from the IEEE Ok anagan Subsection\, IEEE Okanagan College Student Branch and Computer Scie nce Department: Dr. Youry Khmelevsky\, Chair (9:30 am &ndash\; 9:35 am)<br >2. Invited speaker from the University of Paris East Creteil: Dr. Ga&eacu te\;tan Hains (9:35 am &ndash\; 10:15 am)<br>3. Invited speakers from Lang ara College: Dr. Albert Wong &amp\; Andres C. Viloria Garcia (10:15 am &nd ash\; 11:00 am)<br>&ensp\;&ensp\;&ensp\;&ensp\;&ensp\;&ensp\;Machine Learn ing algorithms for stock price forecasting<br>&ensp\;&ensp\;&ensp\;&ensp\; &ensp\;&ensp\;Model building process and methodology<br>&ensp\;&ensp\;&ens p\;&ensp\;&ensp\;&ensp\;Normalization and performance evaluation<br>&ensp\ ;&ensp\;&ensp\;&ensp\;&ensp\;&ensp\;Iterations and results<br>4. Coffee Br eak (11:00 am - 11:15 am)<br>5. Student research project presentation and demonstration (11:15 am - 12:30 pm)<br>&ensp\;&ensp\;&ensp\;&ensp\;&ensp\; &ensp\;Database design<br>&ensp\;&ensp\;&ensp\;&ensp\;&ensp\;&ensp\;Data c ollection process automation<br>&ensp\;&ensp\;&ensp\;&ensp\;&ensp\;&ensp\; Extraction\, Transformation and Loading Process<br>&ensp\;&ensp\;&ensp\;&e nsp\;&ensp\;&ensp\;UI development for data configurations and extraction<b r>&ensp\;&ensp\;&ensp\;&ensp\;&ensp\;&ensp\;Integration prototype using Ju pyter notebooks</p>\n<p>We will demonstrate how to evaluate the quality of the collected data\, the metrics of the machine learning model&rsquo\;s p rediction\, and their integration.<strong>&nbsp\;</strong></p> END:VEVENT END:VCALENDAR