Big data and NLP technologies to collect, structure, and reveal events from news articles, press releases, and financial social media and share it with our clients via dashboards or API

DATA FOR ALPHA

Big data and NLP technologies to collect, structure, and reveal events from news articles, press releases, and financial social media and share it with our clients via dashboards or API

DATA FOR ALPHA

Sophisticated investors are increasingly augmenting their decision-making processes using alternative data sources from news and social media.

In today’s noisy environment, it is essential to have a bigger and clearer picture of companies and countries financial activities by being able to collect, structure, and reveal important events in order the capture alpha.

Using big data and NLP technologies powered by dedicated classifiers, dictionaries and clusters for the financial industry, provides the opportunity to sift through the noise and find only the relevant events which impact financial outcomes of companies and countries.

To empower the technology, a hybrid model of machine and human is being used to provide accuracy of data classification, context, and sources to ensure maximum value for our clients.

The output is accurate and clean dataset which contain only the important events where each is scored based on its impact on the company’s performance, which indicates the direction (bullish/bearish) and duration (long/short term).

The data is presented via visually compelling, interactive dashboards or as CSV file via FTP or API.

Our data and system are being used by world-leading quants, quantamental, fundamental hedgefunds and assets managers.

Coverage

30 Markets

11 Sectors

42 Event Categories

80 HQ Countries

136 Industries

385 Event Subcategories

700 ETFs

7172 Companies

60000 Events in DB

Use case

Quantitative investment models

Dataset

Clean dataset using a hybrid model for accuracy and advance clusters for data relationship
Each event is scored based on its impact on the company’s performance, which indicates the direction (bullish/bearish) and duration (long/short term)
Structure machine-readable dataset
Delivered daily via S3, API, FTP
Trusted by top tier quant shops
A trial period for backtesting

Portfolio managers

Analysis levels

Markets
Sectors
Industries
Companies
ETFs
Portfolio
Countries

Functionality

Friendly and easy to use interface
Event-driven score by date range
ML data query
Key influencer factor indicator
Advance filtering
Export to xls, csv, pdf, ppt
Email and phone alerts on event-driven score changes
Share notes and other information with colleagues to encourage organized collaboration

Privet equity

DDQ on target company

Track corporate events on target company to make data-driven decisions: new product launch, fundraising, expansion to new markets, partnerships, joint venture, acquisition, management change, changes in product pricing model, regulatory decisions, financial reports, and compare the data with public-traded peers

Portfolio companies

Track portfolio companies’ corporate events to monitor their business activities and make the right adjustment to their strategy

Corporate

Competitors monitoring

Track competitor’s corporate events such. new products, management change, M&A, new deals, new agreements, expansion to new markets, ESG and more
Benchmark against other peers and industry performance

October 2019

Alternative data: Netflix outperform in Q3 2019

Netflix outperform in Q3 2019 We saw the shift in Netflix $NFLX from the past quarter using key events that took place during 3Q. The streaming-video pioneer beat subscription estimates thanks to growth in countries like Brazil and India. The third season of Stranger Things helped drive business, drawing [...]

Alternative data: clean dataset and why it’s impotent

Alternative data: clean dataset and why it's impotentToday, more than 80% of the data is unstructured. Data is being produced as we speak – from every conversation we make in social media to every content generated from news sources. In order to produce any meaningful actionable insight from data, [...]

September 2019

Privet Equity Case Study – Snowflake

Privet Equity Case Study - Snowflake Snowflake provides a data warehouse as a service designed for the cloud, founded in 2012 and raised $928M to date. The company is headquartered in San Mateo, California, United States. Snowflake offers corporate users to store and analyze data using cloud-based hardware [...]

August 2019

Sift through the noise

Sift through the noise As data volume increase by the day, the noise level is tremendous. By noise, we mean the same data in different wording or even duplication of the same content. In the financial markets, data is key factor for outperforming the benchmarks. However, nowdays, it [...]

12 Next

Load More Posts

TAKE THE NEXT STEP