BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pydata-london-2026//speaker//FGG7CG
BEGIN:VTIMEZONE
TZID:GMT
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pydata-london-2026-BGNZLQ@pretalx.com
DTSTART;TZID=GMT:20260607T101500
DTEND;TZID=GMT:20260607T110000
DESCRIPTION:Tesco is applying AI and Data Science at scale to solve some of
  the most complex problems in retail. From personalisation to optimisation
  and decision support\, our systems power millions of customer interaction
 s and operational decisions every day. In this talk\, we highlight how the
 se capabilities come together in modern AI-driven customer experiences\, a
 nd why Tesco is at the forefront of applying AI in real-world\, high-impac
 t settings. \n\nWe briefly introduce Tesco’s Meal Planner to highlight t
 he technical challenges behind AI-driven customer experiences. A key chall
 enge behind the scenes is translating recipes into products that customers
  can actually buy. We approach this by connecting recipes\, ingredients\, 
 and products in a way that enables the system to move from meal ideas to a
  ready-to-shop basket. This requires balancing richer reasoning over custo
 mer needs and preferences with the practical realities of a live retail en
 vironment\, such as a constantly changing product catalogue\, cost\, and a
 vailability. \n\nWe then turn to one of the most important aspects of depl
 oying AI systems at scale: Evaluation and how it helps to ensure that the 
 system behaves reliably. When AI assistants support customer journeys\, ev
 en small errors can degrade the experience or lead to incorrect outcomes. 
 We present our evaluation framework\, which combines multiple techniques t
 o assess both system behaviour and response quality. This allows us to ide
 ntify issues early\, enforce consistent standards\, and continuously impro
 ve performance. \n\nOverall\, this talk offers a practical view of how Tes
 co applies AI and Data Science to real-world problems\, combining strong t
 echnical foundations with robust evaluation to deliver reliable and impact
 ful customer experiences.
DTSTAMP:20260623T033822Z
LOCATION:Doddington Forum
SUMMARY:Tesco AI & Data Science: From Recipes to Reality - Julie Huang\, Ka
 reem Hussein
URL:https://pretalx.com/pydata-london-2026/talk/BGNZLQ/
END:VEVENT
END:VCALENDAR