Reducing Friction in
Exploratory Data Analysis
OVERVIEW
Exploratory data analysis is powerful, but often chaotic. Data processing takes too much time, which hinders early user experience.
The goal was to reduce cognitive friction during early analysis—helping users reach meaningful insights faster without overwhelming them.
DESIGN FOCUS
Translating exploratory behaviour into system-level UX decisions
Designing onboarding and analysis flows under uncertainty
Planning for off-boarding
Showcasing signal and insights after data upload.
Behavior-driven UX trade-offs
MarkovML supports data scientists performing early-stage exploratory analysis under time pressure and uncertainty. The following UX trade-offs reflect how exploratory behavior shaped system-level decisions.
BEHAVIORS OBSERVED
Frequent dataset uploads
Early signal-seeking
Interrupted analysis sessions
Ad-hoc sharing (Slack / Teams)
Speed over completeness
Progressive, incremental results with processing feedback
Clarity over density
Delayed advanced visualizations
Memory over novelty
Exploration history with contextual breadcrumbs
Early collaboration over sense making
Shareable insights with embedded findings and metadata
Handling User Activation
Exploratory Data Analysis (EDA) comprises of multiple advanced analysis to be done on data. Which means “More time” needed for analysis to be done.
USER SYMPTOMS
No immediate “Aha” moment for first-time users
Delayed value perception
Increased early drop-offs
1.1 Intent-driven onboarding using analysis themes
By grouping analyses into themes, users explicitly signal what they care about—allowing the system to prioritise relevant analysis instead of running everything upfront.
All analysis types are grouped into themes.
1.2 Reduce uncertainty transparent through progress and early insights
The platform makes analysis progress visible while revealing familiar insights from an existing playbook—keeping users informed, engaged, and oriented.
Transparent success screen after data upload.
IMPACT
Faster time-to-first-insight and reduced early session drop-offs.
Insight Overload
EDA surfaces many insights at once, but without prioritisation, users struggle to understand what matters, slowing sense making and increasing early drop-offs.
USER SYMPTOMS
Cognitive overload from dense insights
Delayed understanding of data quality and risks
Analysis paralysis
Replace open-ended exploration with guided signals
Rather than leaving users to navigate insights freely, the system provides a clear signals—helping users focus on the most impactful issues first and move forward without analysis paralysis.
Guided signals leading user to deeper understanding.
Deep exploration with AI-assisted reasoning
Users can dive deeper into the data whenever required, exploring specific insights and underlying patterns. AI supports this process by helping interpret results and surface relevant context.
AI assisting further understanding during EDA exploration.
IMPACT
Guided exploration reduces cognitive load and accelerates time-to-insight.
Context loss during exploration
As users navigate across charts, metrics, and views, the reasoning behind insights gets fragmented—making it hard to retain context and build confidence.
USER SYMPTOMS
Loss of reasoning behind why an insight mattered
Increased reliance on memory or external notes
Reduced confidence in decisions due to missing context
Continuity across analysis sessions
The system preserves analysis sessions as they evolve, allowing users to revisit past work, recall why insights mattered, and continue exploration without redoing earlier steps.
Tracking all analysis, allows user to resume their exploration after interruptions.
Sharing insights with findings
Exploratory analysis is often shared as isolated screenshots or charts, stripping away the reasoning, assumptions, and conclusions behind them. Without context, collaborators see what the chart shows but miss why it matters—leading to misinterpretation and repeated work.
USER SYMPTOMS
Insights lose meaning when shared outside the analysis environment
Teammates lack clarity on how conclusions were derived
Increased back-and-forth to explain context and intent
Preserving context while sharing insights
Insights are shared as complete analysis reports—not isolated screenshots—so charts always travel with their findings and reasoning. This keeps context intact, reduces misinterpretation, and helps teams align faster without repeated explanations.
