QSentia investment research platform
More alpha. Less unmanaged risk.
Qsentia helps investors evaluate machine-learning strategies with live performance telemetry, benchmark context, drawdown controls, and execution evidence in one workspace.
GET /api/dashboard
Live response preview
{
"model": "Model not selected",
"source_repo": null,
"logs_path": null,
"portfolio_value": null,
"portfolio_return": null,
"sharpe": null,
"portfolio_history": null,
"updated_at": null
}Product surface
Build on source-of-truth telemetry
These modules connect model discovery, portfolio telemetry, execution review, and benchmark analytics into a disciplined diligence workflow.
Model Registry API
Registered strategies, repositories, branches, and log paths keep model diligence organized.
Portfolio Telemetry
Normalized equity curves, drawdown context, and return quality help evaluate alpha persistence over time.
Execution Audit
Decision history, paper status, submitted orders, and run timestamps support operational risk review.
Model registry
Strategy names, sources, rows, and status are read from the dashboard API.
| Model | Source | Rows | Return | Sharpe | Status |
|---|---|---|---|---|---|
| Loading model registry. | |||||
Source details
- Registry
- Not available
- Branch
- Not available
- Model source
- Not available
- Logs path
- Not available
Execution audit
- Paper status
- Not available
- Paper replay status
- Not available
- Last run
- Not available
- Portfolio timestamp
- Not available
- Submitted orders
- 0
- Decision rows
- 0
Selected model equity index
This is an index-style track record for the selected strategy. The first portfolio observation is set to 100, so values above 100 show cumulative gain over the displayed window.
Retrieving selected-model telemetry.
Benchmark comparison
Retrieving market comparison data.
Mission, vision, objective
Building trust in systematic investing
Qsentia exists to make quantitative strategy evaluation more transparent, disciplined, and usable for investors who need evidence before conviction.
Unify model telemetry, research context, and audit trails so investors can evaluate strategies from verifiable source data.
Become the trusted intelligence layer for machine-learning driven investment research, diligence, and model monitoring.
Give users a clear path from model discovery to live telemetry, benchmark comparison, and professional due diligence review.