"machine learning-based predictions" ?

[tv42]

My apologies for the delivery but the README looks like vibecoded AI slop.

Claude-Code-Usage-Monitor/README.md

Line 8 in 06f0fe1

A beautiful real-time terminal monitoring tool for Claude AI token usage with advanced analytics, machine learning-based predictions, and Rich UI. Track your token consumption, burn rate, cost analysis, and get intelligent predictions about session limits.

Claude-Code-Usage-Monitor/README.md

Line 51 in 06f0fe1

- **🔮 ML-based predictions** - P90 percentile calculations and intelligent session limit detection

Claude-Code-Usage-Monitor/README.md

Lines 484 to 488 in 06f0fe1

	#### 🔮 Machine Learning Predictions
	- **P90 Calculator**: 90th percentile analysis for intelligent limit detection
	- **Burn Rate Analytics**: Multi-session consumption pattern analysis
	- **Cost Projections**: Model-specific pricing with cache token calculations
	- **Session Forecasting**: Predicts when sessions will expire based on usage patterns

I see no ML here, just basic math and some applied statistics:

Claude-Code-Usage-Monitor/src/claude_monitor/ui/display_controller.py

Lines 631 to 676 in 06f0fe1

	def calculate_cost_predictions(
	self,
	session_data: Dict[str, Any],
	time_data: Dict[str, Any],
	cost_limit: Optional[float] = None,
	) -> Dict[str, Any]:
	"""Calculate cost-related predictions.
	Args:
	session_data: Dictionary containing session cost information
	time_data: Time data from calculate_time_data
	cost_limit: Optional cost limit (defaults to 100.0)
	Returns:
	Dictionary with cost predictions
	"""
	elapsed_minutes = time_data["elapsed_session_minutes"]
	session_cost = session_data.get("session_cost", 0.0)
	current_time = datetime.now(timezone.utc)
	# Calculate cost per minute
	cost_per_minute = (
	session_cost / max(1, elapsed_minutes) if elapsed_minutes > 0 else 0
	)
	# Use provided cost limit or default
	if cost_limit is None:
	cost_limit = 100.0
	cost_remaining = max(0, cost_limit - session_cost)
	# Calculate predicted end time
	if cost_per_minute > 0 and cost_remaining > 0:
	minutes_to_cost_depletion = cost_remaining / cost_per_minute
	predicted_end_time = current_time + timedelta(
	minutes=minutes_to_cost_depletion
	)
	else:
	predicted_end_time = time_data["reset_time"]
	return {
	"cost_per_minute": cost_per_minute,
	"cost_limit": cost_limit,
	"cost_remaining": cost_remaining,
	"predicted_end_time": predicted_end_time,
	}

https://github.com/Maciek-roboblog/Claude-Code-Usage-Monitor/blob/06f0fe11e694b8619f63f8b0db10dbdc5e7e5a44/src/claude_monitor/data/analysis.py