Tidal Wertgrove data analysis platform displayed across a working setup used to monitor cross-exchange portfolios

AI-driven portfolio analysis

Cross-exchange data, analysed and ranked by risk, in a single dashboard

Tidal Wertgrove ingests positions and market data from multiple exchanges, applies predictive models to assess volatility and correlation, and returns a ranked set of recommendations you can act on from anywhere.

Access Dashboard Review Methodology

Ingestion — API pulls across connected exchanges on a fixed schedule

Analysis — pattern recognition against historical baselines

Output — risk-flagged recommendations, not blanket guarantees

The problem with manual tracking

Fragmented data creates blind spots in fast-moving markets

Monitoring several exchange accounts by hand works until the number of positions, currencies, or time zones increases. For digital nomads, the added variable of travel — shifting working hours, unreliable connectivity, inconsistent review schedules — compounds the problem further.

Spreadsheets and browser tabs do not scale once asset classes multiply, and manual analysis under volatile conditions carries a real cost: decisions made on stale or incomplete data.

Reconciling balances across exchange APIs manually consumes hours each week.
Price discrepancies between venues are easy to miss without continuous monitoring.
Time-zone shifts while travelling disrupt consistent portfolio review.
Risk exposure is difficult to quantify without a standardised baseline across assets.

Tidal Wertgrove team reviewing cross-exchange portfolio data and analysis workflow

Unified dashboard

One dashboard, consolidated across every connected exchange

Balances, open positions, and risk flags are normalised into a single view, regardless of which exchange or custodial platform holds the underlying asset. Figures are refreshed on a defined interval rather than streamed continuously, which keeps API usage within exchange rate limits while remaining current enough for strategic review.

Each position is tagged with its source venue, last-updated timestamp, and a risk indicator derived from the methodology below, so discrepancies between exchanges are visible rather than hidden inside aggregate totals.

Supported connection types

Spot exchange accounts
Derivatives platforms
Custodial wallet balances
UK and EU-regulated venues

Connections use read-only API keys where the exchange supports this permission level; no withdrawal access is requested.

How it works

Three stages, from raw data to a ranked recommendation

The process is deliberately linear. Each stage produces an output that feeds directly into the next, which keeps the logic auditable rather than opaque.

STEP 1

Data ingestion

Order books, account balances, and historical price series are pulled from each connected exchange via API on a fixed schedule, then normalised into a common format for comparison.

STEP 2

Pattern analysis

Predictive models assess volatility, correlation between assets, and momentum against historical baselines, flagging deviations that fall outside expected ranges.

STEP 3

Risk-adjusted recommendation

Outputs are ranked by a risk-mitigation filter rather than raw predicted return, surfacing the actions most consistent with a stated risk tolerance.

Practical application

Where the methodology is applied in practice

Portfolio automation while travelling

Rebalancing rules can be set once and reviewed on a schedule that suits irregular working hours, rather than requiring real-time attention. The dashboard flags when a position drifts outside its target allocation, so review time is spent on exceptions rather than routine checks.

Hedging against volatility

Correlation data across holdings is used to identify concentration risk — for example, several positions that tend to move together during periods of market stress. Recommendations highlight where a hedge or reduction in exposure may reduce overall portfolio variance.

Cross-exchange price monitoring

Price differences for the same asset across connected venues are surfaced as they appear. The platform flags the discrepancy and the size of the spread; execution remains a manual decision, accounting for transfer times and fees between exchanges.

Transparency

Technical detail, for readers who want to verify before relying on it

These answers are intentionally specific. If a question you have is not covered here, the contact page is the right next step.

How is account data secured?

Exchange connections use read-only API keys wherever an exchange offers that permission level, which means the platform cannot initiate withdrawals or transfers. Credentials are encrypted at rest, and access logs are retained to support audit review.

What are the limitations of the predictive models?

Models are backtested against historical price data, but past patterns do not guarantee future performance. Accuracy varies by asset class and market regime, and recommendations are presented with a risk indicator rather than a single confidence figure, so the underlying uncertainty remains visible.

How does API connectivity work across exchanges?

Each exchange has its own rate limits and authentication requirements; the platform schedules data pulls to stay within those limits rather than polling continuously. If an exchange API is temporarily unavailable, the dashboard marks affected balances as stale rather than displaying unverified figures.