AI Clarity: Legacy data providers have discrepancies of more than 20% in 13% of direct emissions data

New York City–() –Clarity AIToday, the leading global sustainability technology platform announced that of the nearly 6,500 public companies reporting direct emissions, the top data providers have discrepancies in this reported data 42% of the time, with the discrepancy accounting for any difference of more than 1%. When the discrepancy limit is increased to more than 20%, major data providers have discrepancies of about one in eight data points.

“These significant discrepancies in the 13% of data could increase or decrease the Climate Fund’s carbon footprint by more than 20% and highlight the real challenges investors face when choosing a data provider,” said Patricia Pena, head of product research. and innovation in Clarity AI. “Data reliability is at the core of what we do, and we see huge benefits in using advanced technology to help ensure quality.”

Clarity AI has identified three problem areas that purveyors of legacy data can encounter when collecting data:

  1. Human error: Human errors account for more than 80% of errors found. These vary in nature but some examples include: incorrect addition of category values, misinterpretation of report details, inaccurate unit measurements (eg tons vs gigatons)

  2. Inconsistent reporting limits: data providers use limits (i.e. rules to decide which entities from the group should be included or not, what to do with joint ventures, investments, etc.) to report emissions inconsistently

  3. Incomplete disclosures: Companies publish incomplete disclosures that omit relevant emissions (eg, Scope 3 categories, regions/offices, lines of business)

“At Clarity AI, we rely on technology and data to solve reliability issues. First, we curate a robust data set of sustainability data points, which have undergone rigorous quality checks. Next, we train, calibrate, and validate an expert-supervised machine learning model to identify the most reliable data points. and filter out unreliable data,” added Ron Potock, Head of Data Science at Clarity AI. “The flexibility of the machine learning model allows for more complex relationships between the reliability of a data point and its features. The model analyzes data from all angles at every level of detail, which enhances its performance.”

Advanced technology, such as machine learning, is the only scalable and effective way to create clean, reliable data that investors can rely on. Clarity AI has trained the latest machine learning algorithms that leverage input from sustainability experts and is the only sustainability technology provider on the market with a cutting edge machine learning reliability algorithm. Furthermore, algorithms and models only improve with time and constant care from advanced technology experts, because when a data point is detected as unreliable, it is sent for external review (i.e. to the expert panel) and corrected if necessary. Then, this data will return to the system and further train and improve the model in a virtuous cycle.

—————-

About Clarity AI

Clarity AI is a sustainable technology platform that uses machine learning and big data to deliver environmental and social insights to investors, organizations and consumers. As of August 2022, the Clarity AI platform analyzes more than 50,000 companies, 320,000 funds, 198 countries, and 188 local governments—2-13 times more than any other market player—and delivers data and analytics for investment, company research, and benchmarking. . Consumer e-commerce and reporting. Clarity AI has offices in North America, Europe and the Middle East, and its network of clients manages tens of trillions of assets under management. Clarity

Leave a Comment