Home
Applied Research ProjectEMBA 26 · SP Jain
A Behavioural Intelligence Framework

Predicting
the why.

Understanding human action in AI systems — proposing ABSD: Action · Behaviour · State · Drive.

Researcher
Arunamirtharaj Chandrasekar
Academic Mentor
Himmat Singh
Industry Mentor
Akshith Sharma · Brained
01 / HookPredicting the Why
The uncomfortable truth

AI sees everything.
It understands almost nothing.

When a student pauses for thirty seconds before a math problem, the system records the pause and moves on. It cannot tell confusion from careful thinking, anxiety from strategic deliberation.

AI tracks what. It misses why.

02 / 12
01 / HookPredicting the Why
The data scale

The data is there. The interpretation isn't.

500B+
events logged daily by Netflix and Spotify — individually.
73%
of companies struggle to use behavioural data for anything beyond basic segmentation. (Forrester 2022)

Chatbots handle 85% of customer interactions at leading companies. Recommendation engines shape what 2 billion people see daily. Adaptive learning platforms guide millions of students. The systems that understand users deeply will outperform those that only track them.

03 / 12
02 / The problemPredicting the Why
Why the gap persists

Three structural reasons.

REASON 01

Actions are easy to measure. States are not.

Clicks and timestamps capture automatically. Emotions and motivation do not show up in server logs — they must be inferred from patterns most AI development skips.

REASON 02

The relevant research is scattered.

Psychologists study motivation but lack computational tools. Computer scientists build pattern recognition but lack theoretical grounding. Cross-citation is minimal.

REASON 03

Incentives favour optimization over understanding.

When engagement metrics become KPIs, systems optimize for time-on-platform rather than user goal achievement. Personalisation stays on the surface.

04 / 12
03 / Literature gapPredicting the Why
Literature gap

Four rigorous traditions. None talking to each other.

Tradition
What it explains
What it misses
ABSD contribution
Self-Determination Theory
Why people engage: autonomy, competence, relatedness needs.
How to detect need states from behaviour in real time.
Drive layer with behavioural indicators.
Affective Computing
How to detect emotions from multimodal signals.
Connection to motivation; cross-domain application.
State layer mapped to behavioural patterns.
JITAI Research
When to intervene: vulnerability and receptivity windows.
Theoretical grounding in psychology; signals beyond health.
Behavioural signal taxonomy with state mappings.
Learning Analytics
What users do: clickstream, temporal patterns, sequences.
Why users do it: psychological interpretation of patterns.
Action-to-Behaviour pattern detection layer.
05 / 12
04 / FrameworkPredicting the Why
The framework

ABSD — four layers from action to motivation.

Each layer is generated by the one beneath it from the user's perspective. AI must work in reverse — inferring upward from observable Actions.

04
Drive
Motivational · Stable
Why the user does it. Autonomy, competence, relatedness. Inferred over extended interaction.
03
State
Cognitive-Emotional · Momentary
What the user feels. Confusion, confidence, frustration, flow, anxiety.
02
Behaviour
Pattern · Temporal
How the user does it. Hesitation, thrashing, regression, persistence, avoidance.
01
Action
Observable · Discrete
What the user does. Clicks, timestamps, submissions, navigation. What AI tracks today.
06 / 12
04 / FrameworkPredicting the Why
Behavioural signals — the bridge

Seven signals connect action to state.

Signal
Observable pattern
Inferred state
Hesitation
Extended pause; typing then deleting
Uncertainty, low confidence
Thrashing
Rapid switching, no progress
Decision paralysis
Regression
Returning to completed content
Confusion, need to consolidate
Acceleration
Speeding through, minimal engagement
Boredom, overconfidence
Persistence
Continuing effort after failure
High drive, growth orientation
Avoidance
Skipping, minimal time, early exit
Anxiety, helplessness
Flow
Steady progress, low errors
Engagement, optimal challenge
07 / 12
04 / FrameworkPredicting the Why
A critical refinement

Signals are context-dependent.

A 30-second pause before a complex financial trade is prudent deliberation. The same pause before a simple checkout is probably confusion.

Signal-to-state mapping is probabilistic and context-weighted — never deterministic.

MODIFIER 01

Domain context

Industry, task type, interaction norms. Hesitation in healthcare ≠ hesitation in checkout.

MODIFIER 02

User context

Individual baseline, history, expertise. A consistently methodical user isn't hesitating.

MODIFIER 03

Temporal context

Time of day, journey stage, recent UI changes. Spike after redesign signals disorientation, not indecision.

08 / 12
05 / ApproachPredicting the Why
Research approach

Mixed methods. Anchored in customer experience.

This is a conceptual framework study — validation focuses on conceptual coherence, theoretical grounding, and practitioner utility.

01

Literature synthesis

Integrative review across SDT, affective computing, JITAI, learning analytics. Substantially complete.

02

Expert interviews — 5

Semi-structured, 15–20 min. CX primary, EdTech secondary. Thematic analysis (Braun & Clarke).

03

Practitioner survey — 30–50

Descriptive breadth on signal recognition, state inference, framework utility.

04

Case analysis — 2 systems

One CX, one EdTech. Illustrative applications using public documentation.

09 / 12
05 / ApproachPredicting the Why
Four weeks · today

19 May 14 June 2026.

Activities run in parallel. Live progress is at predictwhy.com.

19 – 23 MAY

Lock instruments

Finalise framework, interview protocol, survey. Pilot-test. Outreach to 10–12 interviewees.

24 – 30 MAY

Interviews + survey live

5 interviews, one per day. Survey deployed across LinkedIn, mentor network, EMBA alumni.

26 MAY – 3 JUN

Case analysis

Two AI systems analysed through the ABSD lens using public documentation.

1 – 8 JUN

Coding & synthesis

Thematic analysis. Cross-method refinement of the framework.

6 – 14 JUN

Draft & submit

Mentor review cycles. Final revisions. Submission 14 June 2026.

10 / 12
06 / DeliverablesPredicting the Why
What the project delivers

Three artefacts. Theoretical + practical.

Theoretical

A synthesised conceptual framework connecting four siloed research traditions. Shared vocabulary across layers of Action, Behaviour, State, Drive. Platform for future empirical testing.

Practical

Design heuristics for state-aware AI systems. A diagnostic and implementation guide for organisations moving beyond event counting toward context-aware user intelligence.

Cross-domain

Anchored empirically in CX and EdTech. Transferable to finance, healthcare, and any domain where AI mediates human decision-making.

Quality criteria

Simplicity. Universality. Specificity. Groundedness. Actionability. Validated through practitioner feedback.

11 / 12
07 / Get involvedpredictwhy.com
Read · Take part · Share

This is open research.
Get involved.

01Read the full paper at predictwhy.com
02If you build AI products, take the 5-minute practitioner survey.
03Share it with anyone working on user understanding in AI.
12 / 12