Risk Factors

Unique compilation of the risk factors reported by publicly listed companies along with smart NLP-driven indicators designed to enrich risk management analyses.


Datacie’s Risk Factors dataset is a unique text-mined data solution that offers uncharted insights into the risk factors born by publicly listed companies. Access this unequaled dataset to understand, measure, and make informed decisions about the plenitude of risk factors that surround a business model, a group of companies, or an entire industry from a fresh, qualitative perspective.

Company Coverage

Company coverage

10'000 active and delisted

Geographical Coverage


Largely US & Canada

Data History


Back to 2000

As reported / Standardized

Reporting type


Most-Recent / As Reported


Include both views

Data Frequency



Reporting Lag



Delivery Format

Delivery status

Excel, API, FTP & Datafeed

Use Cases & Benefits

Consultants -help your clients realize the competitive advantages of an effective, risk-informed strategy.

Corporates -obtain an in-depth understanding of the risk factors that your business partners & competitors face and compare your company’s identified risk items to your industry’s standards.

Hedge Funds -devise winning investment strategies that exploit risks’ probability of occurrence miscalculation or the misjudgment of the risks’ severity of consequences.

Financial product managers -develop investment products that concentrate/exclude distinct risk factors.

Institutional managers -measure and report on your products’ integrated risk factors and provide confidence to your clients that require greater transparency around risk management.

Investors -gain full awareness of the risks inherent to your portfolio companies such as client concentration or dependence on a certain product or supplier.

Risk managers -discover new concentration risk, segment idiosyncratic from widespread risk factors, create risk-mitigation strategies by adjusting your exposure to distinct risk factors and perform comprehensive, cross-sectorial risk analyses using self-reported data.

Column definition

company name

Official name of the company.
Ex: Airbnb, Inc.

reporting date

Date for which the information has been publicly available in official disclosures.
Ex: 02.2021


Summary of the risk items as reported.
Ex: The COVID-19 pandemic and the impact of actions to mitigate the COVID-19 pandemic have materially adversely impacted and will continue to materially adversely impact our business, results of operations, and financial condition.


Full description of the risk items as reported.
Ex: In March 2020, the World Health Organization declared the outbreak of COVID-19 a pandemic. In an attempt to limit the spread of the virus, governments have imposed various restrictions, including emergency declarations at the federal, state, and local levels, school and business closings, quarantines, “shelter at home” orders, restrictions on travel, ...

risk category

Accordingly to the disclosure format applied by reporting companies, this column refers to the document’s heading in which the risk item is organized.
Ex: Business

risk topic

Classification scheme that contains five categories in which each risk item is mapped (strategic risk, financial risk, operational risk, compliance risk, and reputational risk).
Ex: Operational

new risk

Binary indicator that takes the value of 1 if the risk item is disclosed for the first time by the reporting entity, 0 otherwise.
Ex: 1

relative position

Relative position of each risk item within their disclosure section. Given that reported risks are typically listed in order of importance, this metric can be used to assess a risk item’s relative importance to a company. It can also be used to compare how businesses within the same industry perceive prevalent risk factors.
Ex: 1

relative position delta

Continuous indicator computed as the difference YoY of the relative position column, highlighting changes in the reporting entities’ prioritization of their risk factors.
Ex: 3

risk sentiment

This indicator takes a value ranging from 0 (a risk item overall sentiment is rather negative) to 1 (a risk item overall sentiment is rather positive) where the midpoint of this continuous scale indicates neutral sentiment. Unlike lexicon-based sentiment analyses, Datacie has developed proprietary NLP algorithms that set a sentiment score based on the readiness of a reporting company to reduce the effect of harmful results described in the risk items. For example, if the company refers to insurance protection or remediation plans in the column description, our models would associate a positive sentiment score to these items.
Ex: 0.87


International Securities Identification Number of the company’s most traded share classes, notes or bonds.


Ticker or trading symbol.


Country in which the securities are listed.
Ex: US


Name of the exchange in which the securities are listed.


Datacie’s Risk Factors dataset is built from preliminary earnings report (PRELIM), quarterly/annual filings (10-Q/10-K), and from Events or Changes Between Quarterly Reports (8-K) – all the SEC filings being sourced from the SEC EDGAR database.
As a trusted data partner, Datacie is committed to delivering competitive and error-free data products to its clients. To this end, we are leveraging our proprietary data extraction technology to capture most of the risk items and their summary automatically from the “Risk Factors” section found in specific SEC filings (see item 105 of regulation S-K). By construction, our technology predicts diverse quality indicators for each data point acquired; our risk management experts then review these quality indicators and carry thorough qualitative investigations of the extracted information, guaranteeing that our risk factors compilations are fully accurate and that no crucial items are missed.
After inception, the entire dataset is audited and evaluated for trustworthiness. Every data entry passes through hundreds of quality checks that automatically identify outliers and potentially misreported observations. Additional manual checks are performed on low-confident data points, ensuring that the final data product is free from poor-quality observations.

Status & Delivery

The Risk Factors dataset is currently being compiled and prepared for our clients’ preferred usage; additional coverage (temporal and company-wise) and existing/new columns can be modified/added on demand. Contact us and be among the first to benefit from this data solution to inform your risk-related decisions with the highest quality, cost-effective data of the market.

Datacie Sàrl

Postal address

EPFL Innovation Park - Le Garage

Chemin de la Raye 13

CH-1024 Ecublens

About us

Datacie is an information company specializing in Document Intelligence that provides unique, actionable and fully customizable datasets to financial institutions, global corporations and non-profit organizations. Our mission is to empower research and decision-making by democratizing access to high-quality, professional-graded datasets directly built from the world's most trusted content sources.

Leave us a message

© 2021 Datacie Sàrl. All rights reserved.