Tweet
Tweet

Slide 1

Slide 1 text

CAREForMe: Contextual Multi- Armed Bandit Recommendation Framework for Mental Health New Idea Track

Slide 2

Slide 2 text

1 in 4 people are affected by mental illness worldwide 56% adults with mental illness receive no treatment $280 billion spent on mental health in the U.S. in 2020 2 Mental Health Crisis

Slide 3

Slide 3 text

AI Chatbot Meditation Apps Health Tracking Apps …… 3 mHealth Solutions Low Cost 24/7

Slide 4

Slide 4 text

AI Chatbot Meditation Apps Health Tracking Apps …… 4 mHealth Solutions Low Cost 24/7

Slide 5

Slide 5 text

Easier said than done! 5 Ideal Reality I know what to do. I’ll be happy ever after! Wait what now? Breathe? Meditate? Gratitude? NOOOOOO I’m a LOSER!

Slide 6

Slide 6 text

CAREForMe Cares Just-in-Time No burden on the user to initiate help Understand user context & situation Just-in-time support Personalization No same general advice No slow start to understand user Continuous learning from similar users Modularity No ad-hoc pipeline Separation of concerns Customizable & flexible framework 6

Slide 7

Slide 7 text

CAREForMe CMAB Recommendation Framework 7

Slide 8

Slide 8 text

CAREForMe CMAB Recommendation Framework 8

Slide 9

Slide 9 text

CAREForMe CMAB Recommendation Framework 9

Slide 10

Slide 10 text

CAREForMe CMAB Recommendation Framework 10 3 ChatBots https://github.com/ANRGUSC/mab-reco

Slide 11

Slide 11 text

What is Contextual Multi- Armed Bandit (CMAB)? 11

Slide 12

Slide 12 text

What is Contextual Multi- Armed Bandit (CMAB)? 12 No need to know which machine works better!

Slide 13

Slide 13 text

Why Contextual Multi- Armed Bandit (CMAB)? AI Technique with continuous learning (NOT LLM😂) Small, tailored models à low cost, accessibility 13

Slide 14

Slide 14 text

Why Contextual Multi- Armed Bandit (CMAB) AI Technique with continuous learning (NOT LLM😂) Small, tailored models à low cost, accessibility 14

Slide 15

Slide 15 text

Why Contextual Multi- Armed Bandit (CMAB) AI Technique with continuous learning (NOT LLM😂) Small, tailored models à low cost, accessibility Adaptive when learning from new data (no retrain) Handle “cold start” problem Context-aware & personalized 15

Slide 16

Slide 16 text

Why Contextual Multi- Armed Bandit (CMAB) AI Technique with continuous learning (NOT LLM😂) Small, tailored models à low cost, accessibility Adaptive when learning from new data (no retrain) Handle “cold start” problem Context-aware & personalized 16

Slide 17

Slide 17 text

Easier said than done! 17 Ideal Reality I know what to do. I’ll be happy ever after! Wait what now? Breathe? Meditate? Gratitude? NOOOOOO I’m a LOSER!

Slide 18

Slide 18 text

Easier to do & I CAN DO IT! 18 Home Work Great job meditating! This will help you maintain your cool 😎 Hi there, finding it hard to relax? It’s normal! Why not put on some relaxing music?

Slide 19

Slide 19 text

Easier to do & I CAN DO IT! 19 Home Work Great job meditating! This will help you maintain your cool 😎 Hi there, finding it hard to relax? It’s normal! Why not put on some calming music? Or take a walk?

Slide 20

Slide 20 text

CAREForMe’s Vision Reference pipeline for new comers Foster interdisciplinary collaboration Living repository for JITAI recommendation systems beyond mental health 20

Slide 21

Slide 21 text

CAREForMe: Contextual Multi- Armed Bandit Recommendation Framework for Mental Health New Idea Track

Slide 22

Slide 22 text

Thanks! CAREForMe: https://tinyurl.com/careforme2024 Email: [email protected] LinkedIn: www.linkedin.com/in/yixue-zhao/ Twitter/X: @yixue_zhao 22