What this page covers

This page gathers the practical details behind Delunavora: what our tools actually do, how we apply AI, and where implied expectations analytics fit into real workflows. We focus on teams who already work with derivatives data but want a more coherent view of what markets are implying about macro paths and equity themes. Our systems ingest options, futures, and swaps data into documented pipelines, then apply AI models tuned to highlight structure rather than noise. The outputs are comparison tables, scenario summaries, and concise charts that can be dropped into research packs, committee decks, or internal memos. We call the core framework the Implied Expectations Map. It organises signals by horizon, instrument, and topic so that disagreements become visible instead of buried in specialist reports. Around that core, we maintain processes for data provenance, scenario review, and governance documentation. We do not offer personal investment advice or promote specific trades. Past performance does not guarantee future results, and results may vary.

Internal frameworks we rely on

A closer look at the internal frameworks that structure how we read, document, and revisit implied expectations from derivatives markets.
Behind the terminology on this page are a few internal frameworks that keep our work consistent and reviewable.
The Implied Expectations Map is our way of organising derivatives signals into coherent scenarios. It groups options, futures, and swaps data by horizon and topic, then uses AI to highlight where markets embed narrow ranges, wide uncertainty, or asymmetric risks. This framework is designed to be stable over time so that teams can compare current views with prior periods without constantly relearning how the outputs are structured. It also makes it easier to document why a particular scenario was considered relevant at a given moment.

Data Provenance Trace is the set of practices we use to track how derivatives data moves through our systems. For each figure in an implied expectations table, we record sources, transformation steps, and key configuration choices. This level of detail supports internal governance and helps teams respond to questions from oversight bodies about how AI models and market data were used. Past performance does not guarantee future results, and results may vary.

Scenario Review Loop is our process for periodically revisiting past implied expectations views. Rather than treating historical scenarios as successes or failures, we analyse how markets and models interacted, which assumptions held, and which broke. The goal is to refine our methods and documentation, not to rewrite history. This loop helps teams build institutional memory around how they interpret derivatives based expectations over multi year horizons.

How we think

Our work at Delunavora revolves around one task: turning derivatives prices into structured statements about how markets see the future. We use AI to read implied expectations from options, futures, and swaps, then align those signals into comparison tables and scenarios that research and risk teams can interrogate. The focus is not prediction; it is clarity about where markets agree, where they diverge, and how those tensions evolve across maturities. Every method we use is documented so a sceptical colleague can follow the logic without reading code. Past performance does not guarantee future results, and results may vary.
  • Aligning options, futures, and swaps into a single implied expectations map for macro and equity research teams.
  • Documenting each step from raw derivatives data to scenario ready tables and charts.
  • Designing outputs that can be read and challenged by non specialists in derivatives or AI.
  • Embedding governance needs, audit trails, and clear caveats into everyday analytical workflows.
  • Reviewing past scenarios through a structured loop to understand what held and what changed.
Transparency in analytics

We design AI tools so that every number in an implied expectations table can be traced back to its data source, transformation steps, and scenario rule, making internal review and governance straightforward.

Respect for market tension

Our work focuses on reading options, futures, and swaps together, highlighting where markets disagree with prevailing narratives instead of chasing a single, fragile forecast.

Durable methodologies

We build methods that can withstand changing regimes, instruments, and data vendors, prioritising durability over novelty so research teams can rely on stable workflows.

Human centred decisions

We aim to support human judgement, not replace it, giving macro and equity teams clear comparison views that sharpen debates rather than dictate outcomes.

Important context and limitations

Understanding how we position AI based implied expectations analytics within real world constraints, governance requirements, and the limits of market data.

The information on this page is designed to answer detailed questions about how we work, not to promote specific trades or outcomes.
We treat implied expectations analysis as a technical discipline that supports, rather than replaces, human judgement. Our AI models help identify structure in options, futures, and swaps data, but every scenario they produce is subject to review and interpretation by experienced teams. We are explicit about model assumptions, data limitations, and the possibility of structural breaks. Markets can and do behave in ways that fall outside historical patterns, which is why we avoid promising particular outcomes and instead focus on clarity and documentation.

Because we operate from Canada and work with organisations that have formal governance processes, we design our tools to fit into existing oversight structures. That includes clear records of how data was handled, how AI models were configured, and how scenario rules were applied at a given time. These records help risk, compliance, and audit teams evaluate the appropriateness of using implied expectations analytics in their own contexts. Past performance does not guarantee future results, and results may vary.

Nothing on this page, or elsewhere on the site, constitutes personal investment advice, legal advice, tax advice, or any other form of personalised recommendation. References to options, futures, swaps, or implied expectations are provided for informational and analytical purposes only. Before making decisions that could affect your financial position or regulatory obligations, you should seek independent professional advice that takes your specific circumstances into account.
  1. 01
  2. 02
  3. 03

Considering collaboration with Delunavora

What to expect if you decide to explore AI based implied expectations analytics with our team, and how we approach potential collaborations.

For teams considering whether to work with us, a few practical points often shape the decision.

We focus on organisational users involved in macro and equity research, strategy, treasury, and risk functions. Our tools are designed to plug into existing processes where derivatives signals already matter but are difficult to keep aligned across instruments and meetings. We do not build retail facing products or tools intended for individual investors. Instead, we concentrate on scenarios where clear documentation, auditability, and long horizon thinking are central requirements.

Implementation typically starts with a conversation about your current data sources, governance expectations, and the specific decisions that rely on implied expectations. From there, we explore how our methodologies, such as the Implied Expectations Map and Data Provenance Trace, could complement or inform your own systems. Any collaboration respects your internal controls and regulatory obligations, and we encourage independent legal and compliance review before adopting new analytical approaches. Past performance does not guarantee future results, and results may vary.
If you want to discuss these topics further, you can reach our team through the contact details provided on the contact page. Sharing information about your time horizon, internal audiences, and existing use of options, futures, and swaps data helps us determine whether a deeper conversation makes sense. We respond with an emphasis on clarity rather than promises, keeping the focus on whether our approach fits your context.

Practical examples of implied expectations in use

Implied expectations analysis sits at the intersection of derivatives data, AI modelling, and real world research workflows. The examples below show how those pieces fit together in practice, from daily monitoring to deeper scenario work.
team tracking options volatility signals

Daily derivatives monitoring

A macro team starts its day by reviewing a dashboard that summarises changes in options implied volatility across key horizons. Our AI models flag where shifts in skew or term structure differ from recent patterns. These signals feed into an implied expectations table that also includes futures and swaps views. Analysts use the table to identify which topics need discussion in the morning meeting and which can be safely parked. Past performance does not guarantee future results, and results may vary.

committee reviewing scenario tables

Committee ready materials

Ahead of a committee meeting, a strategy team prepares scenario sheets that align internal narratives with derivatives based implied expectations. Options, futures, and swaps data have already been processed through documented pipelines, and the resulting tables show where market pricing supports or challenges each scenario. The team uses these materials to explain why they might lean away from certain implied paths, with clear caveats and references to underlying data.

data and ai teams designing pipelines

Building internal pipelines

A technology group works with our methodology to design internal data flows that mirror the Implied Expectations Map and Data Provenance Trace. They document how derivatives feeds enter their systems, how quality checks are applied, and how AI models are configured. This work ensures that when research or risk teams view implied expectations tables, they can trace each figure back through the pipeline and understand the assumptions involved. Past performance does not guarantee future results, and results may vary.

diagram of implied expectations data flow
Method overview

From raw derivatives to implied expectations

At the centre of our work is the idea that options, futures, and swaps each encode a partial view of how markets see the future. Options surfaces describe distributions, futures curves trace expected levels over time, and swaps term structures capture views on policy and risk sentiment. Our AI models treat these as complementary signals and look for consistent patterns and tensions across them.

The process starts with data ingestion and cleaning, continues through feature construction and scenario rules, and ends with tables that map implied expectations by horizon and theme. At each step we document assumptions and transformations so risk and governance teams can review them. The result is not a single forecast, but a structured set of market implied scenarios that research and strategy teams can compare with their own views. Past performance does not guarantee future results, and results may vary.

How teams use implied expectations analytics

Different teams come to implied expectations analytics with different questions. Some want to understand how derivatives pricing lines up with their macro scenarios; others need committee ready documentation that explains why their internal view diverges from market signals. The sections below outline common ways organisations use our tools and methods, and how we structure conversations around them.

    1

    Macro scenario cross checks

    Macro teams use our implied expectations views to cross check narratives about growth, inflation, or policy paths against derivatives pricing. Options surfaces, futures curves, and swaps term structures are aligned into comparison tables that show where markets cluster around a narrow range and where they price wide uncertainty. This helps teams decide which debates deserve more attention and which are mostly noise.

    2

    Equity research context

    Equity researchers draw on our tools to understand how sector or theme level expectations implied by derivatives compare with bottom up views. By mapping options and related signals into a consistent framework, they can see where markets price asymmetric outcomes or where curves suggest a different timing than their internal models. The goal is to sharpen questions, not dictate conclusions. Past performance does not guarantee future results, and results may vary.

    3

    Risk and governance uses

    Risk and governance teams rely on audit trails and documentation that accompany our implied expectations outputs. Every figure in a table can be traced back to data sources, transformations, and scenario rules, making it easier to explain methods to oversight bodies and regulators. This reduces reliance on opaque scores and supports consistent treatment of derivatives based information across committees.

    4

    Strategy and planning support

    Strategy groups often use our comparison views as a neutral reference point when internal opinions differ. By grounding discussions in how options, futures, and swaps currently embed expectations, teams can separate disagreements about data from disagreements about interpretation. This structure helps keep debates focused and repeatable across meetings and planning cycles.

    5

    Data and infrastructure alignment

    Technology and data teams use our methodology as a template for building or integrating their own infrastructure. The emphasis on named frameworks, such as the Implied Expectations Map and Data Provenance Trace, makes it easier to align internal systems with clear responsibilities for data quality, model configuration, and scenario generation.