BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Denver
BEGIN:DAYLIGHT
DTSTART:20250309T030000
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:MDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:MST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250410T234916Z
UID:3DA0183C-67BF-4FBF-B090-7FAA9B1F8D82
DTSTART;TZID=America/Denver:20250410T173000
DTEND;TZID=America/Denver:20250410T190000
DESCRIPTION:Forecasting the demand for new fashion products in the fast fas
 hion industry is a com-\n\nplex task due to its dynamic nature\, short pro
 duct life cycles\, and limited historical data.\n\nTraditional forecasting
  models often fail\, leading to inefficiencies such as overproduc-\n\ntion
  or underproduction. This paper reviews key challenges and explores innova
 tive\n\nmachine learning (ML) and artificial intelligence (AI)-based model
 s to improve fore-\n\ncast accuracy. We propose a hybrid AI-driven approac
 h that integrates structured and\n\nunstructured data sources\, real-time 
 monitoring\, and ensemble models to address fore-\n\ncast limitations in t
 he fast fashion industry.\n\nSpeaker(s): Dileep\, \n\nAgenda: \n5:30-5:35 
 pm - Introductions\n\n5:35-6:35 pm - Presentations\n\n6:35-7:00 pm - Quest
 ions\n\nVirtual: https://events.vtools.ieee.org/m/476734
LOCATION:Virtual: https://events.vtools.ieee.org/m/476734
ORGANIZER:john.santiago@ieee.org
SEQUENCE:32
SUMMARY:Smarter Demand Forecasting for Fast Fashion: Hybrid Models for a Dy
 namic Market
URL;VALUE=URI:https://events.vtools.ieee.org/m/476734
X-ALT-DESC:Description: &lt;br /&gt;&lt;div dir=&quot;auto&quot;&gt;\n&lt;p&gt;Forecasting the demand f
 or new&amp;nbsp\;&lt;span class=&quot;il&quot;&gt;fashion&lt;/span&gt;&amp;nbsp\;products in the fast&amp;nb
 sp\;&lt;span class=&quot;il&quot;&gt;fashion&lt;/span&gt;&amp;nbsp\;industry is a com-&lt;/p&gt;\n&lt;p&gt;plex 
 task due to its dynamic nature\, short product life cycles\, and limited h
 istorical data.&lt;/p&gt;\n&lt;p&gt;Traditional forecasting models often fail\, leadin
 g to inefficiencies such as overproduc-&lt;/p&gt;\n&lt;p&gt;tion or underproduction. T
 his paper reviews key challenges and explores innovative&lt;/p&gt;\n&lt;p&gt;machine l
 earning (ML) and artificial intelligence (AI)-based models to improve fore
 -&lt;/p&gt;\n&lt;p&gt;cast accuracy. We propose a hybrid AI-driven approach that integ
 rates structured and&lt;/p&gt;\n&lt;p&gt;unstructured data sources\, real-time monitor
 ing\, and ensemble models to address fore-&lt;/p&gt;\n&lt;p&gt;cast limitations in the
  fast&amp;nbsp\;&lt;span class=&quot;il&quot;&gt;fashion&lt;/span&gt; industry.&lt;/p&gt;\n&lt;/div&gt;&lt;br /&gt;&lt;br
  /&gt;Agenda: &lt;br /&gt;&lt;p&gt;5:30-5:35 pm - Introductions&lt;/p&gt;\n&lt;p&gt;5:35-6:35 pm - Pr
 esentations&lt;/p&gt;\n&lt;p&gt;6:35-7:00 pm&amp;nbsp\; - Questions&lt;/p&gt;
END:VEVENT
END:VCALENDAR