How customers use IPinfo’s data in Snowflake

Since September 2020, IPinfo and Snowflake have partnered together to make IP data available in the Snowflake Marketplace. This IPinfo-supported integration has enabled a variety of use cases for Snowflake users, ranging from threat intelligence to data security and compliance.

As we begin this two-part series focusing on using IPinfo’s data on Snowflake, it’s important to highlight the value of Snowflake’s platform and common use cases.

Snowflake: A platform built for data usability

As organizations employ AI and machine learning (ML) to improve market share in their industry, data scientists and data engineers need large and disparate datasets for ML modeling. However, much of data scientists’ time is spent gathering data and making it usable rather than creating better models.

Due to legacy systems, data scientists also face slow, complex data pipelines as well as restrictive tools, difficult integrations, and siloed data. All of these problems (and more) create an environment where data scientists lose efficiency as well as a competitive advantage for their organization.

That’s where Snowflake comes in.

They eliminate the time data engineers and data scientists spend on infrastructure management by providing scalable pipelines, data lakes, efficient data preparation, and easy-to-use developer tools, languages, and frameworks, and much more.

All of this leaves more time for developers, data engineers, and data scientists to explore new models and experiment with new tools available in Snowflake’s partner ecosystem.

Snowflake Marketplace and IPinfo’s data

And that’s where IPinfo comes in. We specialize in gathering, maintaining, and improving IP address data so data scientists can improve AI within their organizations. That being said, here are some common questions users ask.

Prioritizing data accuracy

IPinfo prioritizes accurate data. If it’s not accurate, it’s not usable.

Data sources

In 2021 alone, IPinfo processed more than 1 petabyte of data.

We gather these insights from a variety of sources, including our own proprietary sources. During 2021, we built an even larger network of servers to collect traceroute information.

Using triangulation, our team finds or checks IP geolocation. This has led to improved geo-accuracy while also allowing us to derive other uses, such as creating confidence bounds on the geolocation or detecting potential VPN users.

Data cleaning

We’ve also developed a multi-step process to monitor our databases and improve insights.

Backed by our proprietary algorithms and data experts, our IP insights are never stale or out-of-date. Research has confirmed that our industry-leading data is always one of the top three providers when it comes to accuracy.

Tracking trends that affect data usability

IPinfo also stays current with industry changes that affect IP address data usability. For instance, in 2021 Apple launched iCloud Private Relay. Within a short time, we started tracking significant growth in APR traffic.

That’s when IPinfo worked with Apple to enable geoaware privacy features within paid subscriptions, such as the Business plan. As a result, IPinfo users can distinguish APR traffic from other masked identities.

Other trends we’ve tracked are as follows:

• How many IPs change geolocation in a year
• The impact of last-digit IP anonymization
• The most-used VPN services
• The most common ways to mask identities

All this to say, our team looks for trends in IP address data and adjusts accordingly to make data more usable.

Inspiration: How customers are using IPinfo’s data in Snowflake

All of this background information to get to this one point - what are some of the best ways to use IPinfo’s data in Snowflake?

1. Build machine learning fraud prediction models

For starters, we’ve seen IPinfo’s data used to build fraud prediction models. Using IP address data, Snowflake users can enrich transaction data and customer insights to create a fraud score.

Several factors can impact the likelihood of fraud:

• Is the IP address masked?
• How far is the order placement from the shipping location?
• What is the average price per item?

Two of the above factors are directly tied to accurate IP data. Snowflake users can get IPinfo’s Privacy Detection data IP to Geolocation data via the Snowflake Marketplace. Then using a simple join, these 3rd party datasets can be added to existing customer data to create a reliable fraud risk model.

While fraud scoring isn’t one-size-fits-all, check out this guide on fraud prediction models for more inspiration.

2. Medical-related data for new startups

Snowflake also provides a HIPPA and GxP-compatible and HITRUST-certified data pipeline for innovative medical organizations. They provide a variety of data for medical organizations that need to optimize operational efficiency, improve outcome-based care, and much more.

Using Snowflake’s data resources, healthcare innovators can optimize patient outcomes and care delivery. One way IP address data is used by providers is to curate personalized content and services based on the geolocation of individuals.

Additionally, IP insights help medical threat intelligence teams manage vulnerabilities, monitor threats to a brand, detect medical record data breaches, and a variety of other data-driven outcomes.

3. Improve accelerated Adtech revenue

Snowflake marketplace users leverage IPinfo’s data to improve Adtech performance while enabling privacy compliance at scale. Among other benefits of merging IP address data with additional third-party data, Adtech organizations can find better alternatives to third-party cookies and improve attribution at the same time.

4. Threat hunting

Elysium Analytics uses IP address data within Snowflake for threat hunting. They merge data sources from the Marketplace to perform graph analytics and visualization.

For instance, using email data, user traffic, IP insights, and more to detect files associated with ransomware attacks. The benefit of Snowflake is that it allows users to have a single data store for all their data to visualize and search the data for trends and threats.

5. Build data security and compliance

Trustlogix monitors access to sensitive data using a variety of insights, including IP address information. They analyze various Snowflake data security policies and detect possible deviations. Additionally, Trustlogix provides actionable advice based on this data.

In this instance, IP data is used to detect whitelisted IPs, monitor, and detect brute force logins, and monitor unrecognized IPs. We’ve seen these insights used across a variety of industries to improve security and compliance.

For instance, government security operation centers (SOCs) manage their online assets using similar methods. Other educational, corporate, and government organizations monitor employee access to resources.

These are just a few of the ways IPinfo data is used on Snowflake.

Ready to start using IPinfo on Snowflake? Get started today!