Delunavora
Talk to us
Overview Methodology About us Contact
Talk to us

Scenes from our implied expectations work

options volatility surface visualisation

Reading options surfaces

A visual grid showing how implied volatility varies across strikes and maturities, used by our team to spot where options markets diverge from prevailing macro or equity narratives in research discussions.
futures curve comparison charts

Comparing futures curves

Side by side futures curves displayed on a large screen, helping analysts compare how implied expectations for rates or commodities shift across different horizons and contract months over time.
swaps term structure analysis

Analysing swaps curves

A detailed view of swaps term structures, highlighting how forward rates embed expectations about policy paths and risk sentiment across multiple maturities in a single table.

team reviewing scenario tables

Scenario comparison work

Researchers gathered around a table, examining scenario comparison sheets that align implied expectations from options, futures, and swaps with internal macro and equity views.
ai implied expectations dashboard

Implied expectations view

An AI powered dashboard summarising implied expectations across derivatives markets, with clear labels and audit trails to support governance and internal committee review.
macro and equity research meeting

Research teams in action

A mixed group of macro and equity researchers in a meeting room, using our implied expectations tools to test whether their narratives align with signals from derivatives pricing.

Behind the tools are people who have spent much of their careers trying to make sense of markets that refuse to sit still.

Our core team brings together quantitative researchers, macro analysts, and data engineers who have worked on both the buy and sell side of financial markets. That mix matters because implied expectations from options, futures, and swaps are not just technical artefacts; they are the product of incentives, constraints, and imperfect information. We build AI models with those realities in mind, treating every output as a starting point for questions rather than an answer to be followed blindly.

Day to day, our work looks less like glossy dashboards and more like slow, careful iteration. We test new features against archived scenarios, compare them with existing methods, and ask whether the added complexity genuinely helps a team explain its view to an internal committee. If the answer is no, the feature does not ship. This discipline keeps the focus on clarity: better tables, cleaner scenario descriptions, and sharper distinctions between what markets imply and what internal views suggest.

We operate from Canada and work with organisations that value transparency, compliance, and thoughtful use of AI. We do not offer personal investment advice or promote specific trades. Instead, we aim to be a quiet but reliable part of the background infrastructure that helps teams understand how derivatives markets encode expectations over time. Past performance does not guarantee future results, and results may vary.

At the centre of our work is the Implied Expectations Map, a framework for aligning signals from options, futures, and swaps into a coherent set of scenarios. Instead of chasing point forecasts, the framework focuses on ranges, asymmetries, and how those features change across maturities. We combine traditional derivatives analytics with AI models tuned to detect structural shifts rather than short term noise. Every step is documented so that risk and compliance teams can understand exactly how a given view was produced.

Around that core, we maintain supporting processes we call Data Provenance Trace and Scenario Review Loop. The first ensures that any figure in a comparison table can be traced back through vendors, transformations, and quality checks. The second forces us to revisit past scenarios and ask what held up, what failed, and whether the failure came from markets changing or our interpretation being too narrow. These processes are unglamorous, but they keep the work honest and make our tools more useful to teams with formal oversight.

We continuously refine these methods in response to new instruments, regulatory expectations, and user feedback, while staying cautious about overfitting to any single regime. Our goal is not to claim foresight but to offer a stable, transparent way to read implied expectations from derivatives markets. Past performance does not guarantee future results, and results may vary.
team reviewing implied expectations analytics

About our implied expectations team

AI for options, futures and swaps

The work on this page starts where most market dashboards stop. Our team focuses on one narrow question: what do options, futures, and swaps collectively say about implied expectations across macro and equity markets. We build AI systems that treat market prices as statements, not just numbers, and translate those statements into scenarios decision makers can actually debate. Instead of adding another colourful chart, we aim to replace improvised spreadsheets with a shared, explainable view of forward-looking signals. Our background spans quantitative research, macro strategy, and data engineering, which lets us keep the models grounded in how real desks operate. We test every feature against three filters: does it shorten the path from raw derivatives data to a coherent view of expectations, does it make assumptions explicit, and can a sceptical colleague audit the logic without reading code. The result is a set of tools designed for teams planning on a multi-year horizon who still need to answer questions before the next meeting. Past performance does not guarantee future results, and results may vary.
team comparing derivatives market scenarios

Our focus

Why we focus on implied expectations instead of single point forecasts, and how that choice shapes every tool we build for research and strategy teams.

On any trading day, derivatives markets contain more forward-looking information than any single analyst can comfortably track. Our work is to compress that information without flattening the nuance. We maintain side by side views of options, futures, and swaps, then use AI to highlight where those markets point to different implied paths for growth, inflation, or sector dispersion. Teams use these views to pressure test their own narratives, not to outsource judgement. We operate from Canada and work with organisations that treat transparency, documentation, and governance as non-negotiable. Past performance does not guarantee future results, and results may vary.

Contact us

How Delunavora grew out of real research conversations

We started by writing down every time derivatives data disagreed with the main narrative in a meeting, then asked why that disagreement kept being ignored.
The story of Delunavora is mostly a story about frustration with how implied expectations were handled in day to day research meetings.
Before we built anything, our team sat through a long stretch of meetings where derivatives data appeared only as a final slide. Someone would flash a volatility surface or a rate curve, mention that markets were pricing a particular scenario, then move on. The numbers rarely matched the narrative that dominated the rest of the discussion. We started capturing those moments and mapping where options, futures, and swaps were quietly disagreeing with the story in the room.

From there, we built a set of internal notebooks that did one thing: align implied expectations across instruments into comparison tables that a sceptical colleague could read without technical background. Over time those notebooks hardened into the methodology we now call the Implied Expectations Map. The shift from ad hoc scripts to a consistent framework meant we could revisit past calls, understand where our interpretation of market signals had been off, and adjust without rewriting everything from scratch.

Today, Delunavora focuses on giving research, strategy, and risk teams a shared lens on implied expectations rather than a stream of trade ideas. Our AI models highlight where derivatives markets embed tension or asymmetry, but humans still decide what that tension means for their own mandates and constraints. We emphasise documentation, clear caveats, and respect for uncertainty. Past performance does not guarantee future results, and results may vary.

Principles that guide our implied expectations work

We organise our work around a few principles that rarely make it into marketing copy but matter in practice. These principles shape how we design AI models, how we handle derivatives data, and how we support research and strategy teams who rely on implied expectations for longer term planning. They also explain why we sometimes decline feature requests that would look impressive in a demo but add noise to real workflows.
Multi source discipline

We treat every data source as partial and every signal as conditional. Options, futures, and swaps each encode different views of risk and timing, so we avoid collapsing them into a single headline number. Instead we build comparison tables that show where markets agree, where they diverge, and how that pattern has evolved recently. This keeps the conversation anchored in structure rather than anecdotes and makes it easier for teams to explain their reasoning to internal committees.

Explainable pipelines only
Our models are designed to be inspected, not admired. We document every step from raw derivatives data to final implied expectations view, including filters, smoothing, and scenario construction. Users can trace any number back to its origin, which supports governance, audit, and internal review. This approach takes more time than shipping opaque scores, but it aligns better with how serious research and risk teams defend their work.
Designed for real debates

We build for desks that already know their questions. Our tools are not about generating ideas from nowhere; they are about giving structure to debates that are already happening inside investment committees, treasury teams, and research groups. By presenting implied expectations from options, futures, and swaps in consistent formats, we help teams compare their narratives with market pricing and document why they might differ.

Long horizon thinking
We design every feature with a three to five year horizon in mind. That means prioritising durability over novelty and focusing on methods that can survive changes in regimes, instruments, or data vendors. We continuously review our Implied Expectations Map methodology against new conditions, but we avoid chasing short lived signals that cannot be explained to new team members later.

How our approach developed

research team designing derivatives models

The project that became Delunavora started with a simple comparison: how often did derivatives market expectations match the narratives in published research notes. We kept seeing gaps. Implied volatility surfaces pointed one way, rate futures another, and written commentary quietly ignored the tension. Our team decided to treat those gaps as the main object of study. Today we maintain an internal methodology we call the Implied Expectations Map. It combines options, futures, and swaps data with AI models tuned to highlight where markets disagree with consensus scenarios, not to predict a single path. We favour transparent inputs over opaque complexity, so every transformation from raw data to summary view is documented and repeatable. We do not offer personal investment advice or recommend specific trades. Instead, we support research, strategy, and risk teams who want a consistent, auditable view of how market prices embed expectations over different horizons. Past performance does not guarantee future results, and results may vary.