Resonant Analytics Behavioral Data Intelligence
Case Study 002
Financial Text Pipelines
Montreal, QC
Financial Services · Earnings Call Intelligence

Research-grade earnings call corpus

Building a research-grade corpus from raw earnings call JSON - structured, queryable, and ready for behavioral language analysis at institutional scale.

25
Years of transcript data
1,960
Tickers per quarter
100+
Quarters processed
4+
Analytical output layers
Problem

Earnings call transcripts are the richest unstructured signal in public markets - and nearly impossible to use at scale

Decades of executive language, analyst questioning, forward guidance, and crisis communication sit locked in raw transcript format. For researchers and quantitative teams, the barrier isn't access - it's transformation. Getting from raw JSON to a structured, analyzable corpus at the scale of the full public market, across a 25-year window, requires pipeline engineering that most organizations don't have in-house.

The client needed not just transcripts, but a layered dataset: Q&A sections isolated, executive voices separated from analyst voices, multiple output formats for different analytical workstreams - all at a scale that made manual processing entirely unworkable.

Approach / Pipeline

From raw API response to research-ready corpus

Source data was ingested via the API Ninjas earnings call endpoint - returning raw JSON across 1,960 tickers per quarter, spanning 25 years. Each transcript required structural decomposition, speaker identification, section isolation, and transformation into multiple formats optimized for different downstream uses.

API Ninjas endpoint Raw JSON across 1,960 tickers per quarter.
Ingestion and validation Schema normalization and error handling.
Structural decomposition Section identification and speaker parsing.
Output generation Parquet, per-ticker files, full corpus, and analysis layers.
Results / Outputs

Four analytical formats from a single pipeline run

The same source data was transformed into four distinct output formats, each optimized for a different research or analytical use case - eliminating the need for downstream re-processing.

Per-ticker files Individual company corpus across all available quarters - optimized for single-company longitudinal analysis.
Full corpus Parquet Entire dataset in columnar format - queryable at scale for cross-market pattern analysis and model training.
Q&A layer Analyst exchange isolated from prepared remarks - enabling focused analysis of unrehearsed executive language under pressure.
Speaker layer Executive voices separated by role - CEO, CFO, and analyst speech segmented for role-specific behavioral analysis.
Why It Mattered

Behavioral language context changes what you can see in the data

Most earnings call datasets treat transcripts as undifferentiated text. This pipeline was designed from the ground up to preserve the conversational and hierarchical structure of each call - because the behavioral signal lives in that structure. Who is speaking, in what context, in response to what pressure, matters as much as the words themselves.

That design philosophy - informed by six years embedded in behavioral language analytics - is what separates this pipeline from a generic text ingestion job. The architecture reflects an understanding of what the data will eventually need to surface.

"The value of earnings call language isn't in what executives say - it's in how they say it when analysts push back. Getting to that signal requires a pipeline that understands the structure of the conversation, not just the text."

Prepared by Resonant Analytics · Not for distribution