blog Market Intelligence /marketintelligence/en/news-insights/blog/an-alternative-investment-team-harnesses-textual-data-analytics-to-find-new-sources-of-alpha content esgSubNav
In This List
Case Study

An Alternative Investment Team Harnesses Textual Data Analytics to Find New Sources of Alpha


Maritime and Trade Talk Episode 22: Trade and Supply Chain Outlook


Next in Tech Episode 142: Customer experience shopping extravaganza


Next in Tech Episode 143: AI security approaches


Street Talk | Episode 119: Unlocking keys to balance sheet restructurings, bank M&A

An Alternative Investment Team Harnesses Textual Data Analytics to Find New Sources of Alpha


THE CLIENT: A Swiss-based multi-asset management firm with $95 billion in assets under management.

USERS: Alternative Style Premia Team

This Swiss-based investment management firm specializing in alternative investing sought to leverage natural language processing (NLP) to extract valuable insights from earnings call transcripts. Managed as an independent company, the firm has developed long-term partnerships with its clients largely due to its expertise in private markets, liquid alternatives, and multi-asset solutions. Being a principal investor in its own strategies, the company has become a leading global alternative investment specialist.

The investment firm manages various asset classes throughout international markets, including equities, fixed income, private assets, and liquid alternatives. The Alternative Style Premia team is a middle-size group consisting of portfolio managers and quantitative strategists responsible for creating and implementing rule-based investment strategies that exploit various economic, price-based, and fundamental factors driving the cross-section of asset returns. To boost the performance of their market-neutral equity strategies, the team decided to expand the spectrum of investment signals by adding numerical scores derived from quarterly earnings call transcripts.


The investment team was looking to find a trusted provider that could collect, transcribe, and if necessary, translate a vast number of earnings calls from countries around the world and then apply a sophisticated NLP technology to obtain unbroken time series for the relevant sentiment and behavioural metrics.
Pain Points

The investment team needs to make both tactical and strategic decisions. Its members saw the benefits of using natural language processing (NLP) but gathering and maintaining the information as well as developing algorithms would require an extensive amount of time. In addition, the team was concerned about coverage, quality, and reliable data delivery on a daily basis.

They wanted to outsource this task to a reputable provider that offered:

  • A comprehensive set of elaborated sentiment and behavioral metrics that would allow for generating low-correlated investment signals.
  • Machine-readable data enabling full integration into the existing strategy-building process on the trading platform and leveraging the information available on the transcript component level
  • Integrated meta-data to set up sentiment monitoring on the aggregated level (e.g., sector, index, etc.)
The Solution

Solution engineers from S&P Global recommended enhancing the current strategy mix with numerical scores obtained from earnings call transcripts. As the investment firm has been using the CIQ Financial data for building and managing its equity strategies, the new dataset was integrated smoothly into the existing investment framework. The scores are delivered in a structured format facilitating an efficient strategy backtest. The extensive meta-data allows for flexible score aggregation on the industry, geographical, and index levels. The scores are delivered within 90 minutes after the end of the earnings call which enables the investment team a timely reaction to any unexpected news.


Access sentiment and behavioral-based metrics

The Textual Data Analytics (TDA) dataset consists of sentiment and behavioral-based metrics rigorously researched and tested against frequently used quantitative strategies. Users can implement signals from 800+ predictive and descriptive metrics derived from NLP in combination with data from the Professionals and Estimates datasets, with differentiated and additive characteristics. The package encompasses 15 years of history in a machine-readable format.


Quickly link textual data scores with traditional datasets

Users can easily combine the quantified information from earnings calls with traditional datasets to formulate unique, proprietary analytics. They can seamlessly link stock price, estimates, and fundamental company data to help identify new investment signals.


Aggregating textual data scores to monitor market segments

Users can leverage metadata tagging to sync with categorical data, like company's size, industry, or geography. This allows for creating and comparing time series of aggregated scores for customized universes and benchmarks.

Key Benefits

Members of the investment team saw various benefits from subscribing to the Textual Data Analytics package, of which the most important are:

  • Access to an extensive range of sentiment and behavioral scores for companies around the world, which are pre-tagged, structured, and organized.
  • Flexibility of combining the TDA scores with other investment data by leveraging the meta-level tags included in the package.
  • Operationally efficient enrichment of pre-existing strategies with new textual investment signals.
  • Speedy, intraday update of scores allowing for a timely response to unexpected news.
  • Easy access through a data feed.
  • Hands-on technical and product support to address any issues as they arise.

An Alternative Investment Team Harnesses Textual Data Analytics to Find New Sources of Alpha

Download PDF Version
Discover Textual Data Analytics
Get more info