feat(#569): implement Predictive Account Activity Modeling

[Meme11030]

• Add accountActivityModeling.ts with behavioral prediction engine:
  • Weighted exponential smoothing with recencyBias for trend tracking
  • Day-of-week + hour-of-day seasonality multipliers
  • Logistic (sigmoid) active-probability estimation per period
  • Calendar event integration with activity multiplier support
• Pattern detection: daily (hour-of-day), weekly (day-of-week), monthly (day-of-month) recurring activity patterns
• 24×7 activity heatmap generation (hour × day-of-week grid)
• Proactive notification system: high activity, inactivity, pattern change, and calendar event notifications
• Behavior change detection: adapts model when recent activity deviates >30% from historical baseline
• Leave-one-out accuracy estimation (20% holdout)
• Utility to bucket Stellar operation records into ActivityRecords
• API routes: POST /analyze, /predict, /patterns, /heatmap, /notifications, /accuracy, /convert (all under /api/v1/activity)
• 43 unit tests, all passing

Acceptance criteria met:

• Activity predictions with confidence intervals per horizon (day/week/month)
• Recurring pattern identification (daily, weekly, monthly)
• Calendar event integration for scheduled activity
• Proactive notification system
• Model adapts to behavior changes
  closes Predictive Account Activity Modeling #569

[vercel]

@Meme11030 is attempting to deploy a commit to the nanle-code's projects Team on Vercel.

A member of the Team first needs to authorize it.

[drips-wave]

@Meme11030 Great news! 🎉 Based on an automated assessment of this PR, the linked Wave issue(s) no longer count against your application limits.

You can now already apply to more issues while waiting for a review of this PR. Keep up the great work! 🚀

Learn more about application limits