57 Ways to Leave Your (Linear) Lover – A Case Study on Using Insight Predict to Find Relevant Documents Without SME Training

by Association of Certified E-Discovery Specialists (ACEDS)
Contact

A Big Four accounting firm with offices in Tokyo recently asked Catalyst to demonstrate the effectiveness of Insight Predict, technology assisted review (TAR) based on continuous active learning (CAL), on a Japanese language investigation. They gave us a test population of about 5,000 documents which had already been tagged for relevance. In fact, they only found 55 relevant documents during their linear review.

We offered to run a free simulation designed to show how quickly Predict would have found those same relevant documents. The simulation would be blind (Predict would not know how the documents were tagged until it presented its ranked list.) That way we could simulate an actual Predict review using CAL.

We structured a simulated Predict review to be as realistic as possible, looking at the investigation from every conceivable angle. The results were outstanding; we couldn’t believe what we saw. So, we ran it again, using a different starting seed. And again. And again. In fact, we did 57 different simulations starting with relevant seeds (singularly with each relevant document). A non-relevant seed. And a synthetic seed.

Regardless of the starting point, Predict was able to locate 100% of the relevant documents after reviewing only a fraction of the collection. You won’t believe your eyes either.

Complicating Factors

Everything about this investigation would normally be challenging for a TAR project.

To begin with, the entire collection was in Japanese. Like other Asian languages, Japanese documents require special attention for proper indexing, which is the first step in feature extraction for a technology assisted review. At Catalyst, we incorporate semantic tokenization of the CJK languages directly into our indexing and feature extraction process. The value of that approach for a TAR project cannot be overstated.

To complicate matters further, the collection itself was relatively small, and sparse. There were only 4,662 coded documents in the collection and, of those, only 55 total documents were considered responsive to the investigation. That puts overall richness at only 1.2%.

The following example illustrates why richness and collection size together compound the difficulty of a project. Imagine a collection of 100,000 documents that is 10% rich. That means that there are 10,000 responsive documents. That’s a large enough set that a machine learning-based TAR engine will likely do a good job finding most of those 10,000 documents.

Next, imagine another collection of one million documents that is 1% rich.  That means that there are also 10,000 responsive documents. That is still a sizeable enough set of responsive documents to be able to train and use TAR machinery, even though richness is only 1%.

Now, however, imagine a collection of only 100 documents that is 1% rich. That means that only 1 document is responsive. Which means that either you’ve found it, or you haven’t. There are no other responsive documents other than that document itself, so there are no other documents that, through training of a machine learning algorithm, can lead you to the one responsive document. So a 1% rich million document collection is a very different creature than a 1% rich 100 document collection. These are extreme examples, but they illustrate the point that small collections are difficult and low richness collections are difficult, but small, low richness collections are extremely difficult.

Small collections like these are nearly impossible for traditional TAR systems because it is difficult to find seed documents for training. In contrast, Predict can start the training with the very first coded document. This means that Predict can quickly locate and prioritize responsive documents for review, even in small document sets with low richness.

Compounding these constraints, nearly 20% (10 out of 55) of the responsive documents were hard copy Japanese documents that had to be OCR’d. As a general matter, it can be somewhat difficult to effectively OCR Japanese script because of the size of the character set, the complexity of individual characters, and the similarities between the Kanji character structures. Poor OCR will impair feature extraction which will, in turn, diminish the value of a document for training purposes, making it much more difficult to find responsive documents, let alone find them all.

Simulation Protocol

To test Predict, we implemented a fairly standard simulation protocol—one that we used for NIST’s TREC program and often use to let prospective clients see how well Predict might work on their own projects. After making the text of the documents available to be ingested into Predict, we simulate a Predict prioritized review using the existing coding judgments in a just in time manner, and we prepare a gain curve to show how quickly responsive documents are located.

Since this collection was already loaded into our discovery platform, Insight Discovery, we had everything we needed to get the simulation underway: document identification numbers (Bates numbers); extracted text and images for the OCR’d documents; and responsiveness judgments. Otherwise, the client simply could have provided that same information in a load file.

With the data loaded, we simulated different Predict reviews of the entire collection to see how quickly responsive documents would be located using different starting seeds. To be sure, we didn‘t need to do this just to convince the client that Predict is effective; we wanted to do our own little scientific experimentation as well.

Here is how the simulation worked:

  1. In each experiment, we began by choosing a single seed document to initiate the Predict ranking, to which we applied the client’s responsiveness judgment. We then ranked the documents based on that single seed.[1]
  2. Once the initial ranking was complete, we selected the top twenty documents for coding in ranked order (with their actual relevance judgments hidden from Predict).[2]
  3. We next applied the proper responsiveness judgments to those twenty documents to simulate the review of a batch of documents, and then we submitted all of those coded documents to initiate another Predict ranking.

We continued this process until we had found all the responsive documents in the course of each review.

First Simulation

We used a relevant document to start the CAL process for our first simulation. In this case, we selected a relevant document randomly to be used as a starting seed. We then let Predict rank the remaining documents based on the initial seed and present the 20 highest-ranked documents for review. We gave Predict the tagged values (relevant or not) for these documents and ran a second ranking (now based on 21 seeds). We continued the process until we ran out of documents.

Figure 1

As is our practice, we used a gain curve to uniformly evaluate the results of the simulated reviews. A gain curve is helpful because it allows you to easily visualize the effectiveness of every review. On the horizontal x-axis, we plot the number of documents reviewed at every point in the simulation. On the vertical y-axis, we plot the number of documents coded as responsive at each of those points. The faster the gain curve rises, the better, because that means you are finding more responsive documents more quickly, and with less review effort.

The linear line across the diagonal shows how a linear review would work, with the review team finding 50% of the relevant documents after reviewing 50% of the total document population and 100% after reviewing 100% of the total.

The red line in Figure 1 shows the results of the first simulation, using the single initial random seed as a starting point (compared to the black line, representing linear review). Predict quickly prioritized 33 responsive documents, achieving a 60% recall upon review of only 92 documents.

While Predict efficiency diminished somewhat as the responsive population was depleted, and the relative proportion of OCR documents was increasing, Predict was able to prioritize fully 100% of the responsive documents within the first 1,491 documents reviewed (32% of the entire collection). That represents a savings of 68% of the time and effort that would have been required for a linear review.

Second Test

The results from the first random seed looked so good that we decided to try a second random seed, to make sure it wasn’t pure happenstance. Those results were just as good.

Figure 2

In Figure 2, the gray line reflects the results of the second simulation, starting with the second random seed. The Predict results were virtually indistinguishable through 55% recall, but were slightly less efficient at 60% recall (requiring the review of 168 documents). The overall Predict efficiency recovered almost completely, however, prioritizing 100% of the responsive documents within the first 1,507 documents (32.3%) reviewed in the collection—a savings again of nearly 68% compared with linear review.

Third Simulation

The results from the first and second runs were so good that we decided to continue experimenting. In the next round we wanted to see what would happen if we used a  lower-ranked (more difficult for the algorithm to find) seed to start the process. To accomplish that, we chose the lowest-ranked relevant document found by Predict in the first two rounds as a starting seed. This turned out to be an OCR’d document (which was likely the most unique responsive document) to initiate the ranking. To our surprise, Predict was just about as effective starting with this lowly-ranked seed as it had been before. Take a look and see for yourself.[3]

Figure 3

The yellow line in Figure 3 shows what happened when we started with the last document located during the first two simulations. The impact of starting with a document that, while responsive, differs significantly from most other responsive documents is obvious. After reviewing the first 72 documents prioritized by Predict, only one responsive document had been found. However, the ability of Predict to quickly recover efficiency when pockets of responsive documents are found is obvious as well. Recall reached 60% upon review of just 179 documents — only slightly more than what was required in the second simulation. And then the Predict efficiency surpassed both previous simulations, achieving 100% recall upon review of only 1,333 documents—28.6% of the collection, and a savings of 71.4% against a linear review.

Fourth Round

We couldn’t stop here. For the next round, we decided to use a random non-responsive document as the starting point. To our surprise, the results were just as good as the earlier rounds. Figure 4 illustrates these results.

Figure 4

Fifth Round

We decided to make one more simulation run just to see what happened. For this final starting point, we created a synthetic responsive Japanese document. We composited five responsive documents selected at random into a single synthetic seed, started there, and achieved much the same results.[4]

Figure 5

Sixth through 56th Rounds

The consistency of these five results seemed really interesting so for the heck of it we ran simulations using every single responsive document in the collection as a starting point. So, although it wasn’t our plan at the outset, we ultimately simulated 57 Predict reviews across the collection, each from a different starting point (all 55 relevant documents, one non-relevant document, and one synthetic seed).

You can see for yourself from Figure 6 that the results from every simulated starting point were, for the most part, pretty consistent. Regardless of the starting point, once Predict was able to locate a pocket of responsive documents, the gain curve jumped almost straight up until about 60% of the responsive documents had been located.

Gordon Cormack once analogized this ability of a continuous active learning tool to a bloodhound—all you need to do is give Predict the “scent” of a responsive document, and it tracks them down. And in every case, Predict was able to find every one of the responsive documents without having to review even one-third of the collection.

Here is a graph showing the results for all of our simulations:

Figure 6

And here are the specifics of each simulation at recall levels of 60%, 80% and 100% recall.

DocID Percentage of Collection Reviewed to Achieve Recall Levels
60% 80% 100%
27096 4% 15% 29%
34000 2% 11% 32%
35004 4% 12% 32%
83204 3% 11% 32%
86395 4% 14% 32%
93664 2% 13% 32%
98263 3% 11% 29%
98391 2% 13% 32%
98945 3% 11% 32%
99708 4% 12% 32%
99773 2% 10% 32%
99812 2% 11% 32%
99883 2% 12% 32%
99918 5% 14% 32%
100443 4% 12% 32%
100876 3% 13% 32%
101211 4% 12% 32%
101705 3% 14% 31%
101829 3% 11% 31%
102395 3% 13% 32%
102432 4% 14% 32%
102499 2% 9% 32%
102705 3% 14% 32%
103803 4% 12% 32%
105017 2% 14% 32%
105799 3% 13% 32%
106993 2% 12% 30%
107315 2% 14% 32%
109883 4% 12% 32%
110350 3% 15% 30%
112905 4% 14% 32%
117037 4% 12% 32%
118353 4% 14% 32%
119216 4% 15% 32%
119258 2% 12% 32%
119362 2% 10% 32%
121859 3% 11% 32%
122000 4% 15% 29%
122380 5% 11% 30%
123626 3% 10% 32%
123887 3% 11% 32%
124517 3% 14% 32%
125901 3% 14% 32%
130558 2% 14% 32%
131255 4% 10% 32%
132604 2% 10% 32%
136819 3% 14% 29%
140265 4% 13% 32%
140543 4% 12% 32%
147820 3% 14% 32%
154413 4% 13% 32%
238202 4% 12% 32%
242068 4% 12% 32%
245309 4% 16% 32%
248571 4% 12% 32%
NR 3% 14% 32%
SS 2% 13% 31%
Min 2% 9% 29%
Max 5% 16% 32%
Avg 3% 13% 32%

Table 1

As you can see, the overall results mirrored our earlier experiments, which makes a powerful statement about the ease of using a CAL process. Special search techniques and different training starts seemed to make very little difference in these experiments. We saw this through our TREC 2016 experiments as well. We tested different, and minimalist, methods of starting the seeding process (e.g. one quick search, limited searching), and found little difference in the results. See our report and study here.

What did we learn from the simulations?

One of the primary benefits of a simulation as opposed to running CAL on a live matter is that you can pretty much vary and control every aspect of your review to see how the system and results change when the parameters of the review change. In this case, we varied the starting point, but kept every other aspect of the simulated review constant. That way, we could compare multiple simulations against each other and determine where there may be differences, and whether one approach is better than any other.

The important takeaway is the fact that the review order of these various experiments is exactly the same review order that the client would achieve, had they reviewed these documents in Predict, at a standard review rate of about one document per minute, and made the exact same responsiveness decisions on the same documents.

Averaged across all the experiments we did, Predict was able to find just over half of all responsive documents (50% recall) after reviewing only 89 documents (1.9% of the collection; 98.1% savings). Predict achieved 75% recall after reviewing only 534 documents (11.5% of the collection; 88.5% savings).  And finally, Predict achieved an otherwise unheard of complete 100% recall on this collection after reviewing only 1,450 documents (31.1% of the collection; 68.9% savings).

Furthermore, Predict is robust to differences in initial starting conditions. Some starting conditions are slightly better than others. In one case, we achieved 50% recall after only 65 documents (1.4% of the collection; 98.6% savings) whereas in another it took 163 documents to reach  50% recall (3.5% of the collection; 96.5% savings). However, the latter example achieved 100% recall after only 1,352 documents (29% of the collection; 71% savings), whereas the earlier example achieved 100% recall after 1,507 documents (32.3% of the collection; 67.7% savings).

Overall, the key is not to focus on minute differences, because all these results are within a relatively narrow performance range and follow the same general trend.

Other key takeaways:

  1. Predict’s implementation of CAL works extremely well on low richness collections. Starting with only 55 relevant documents out of nearly 5,000 typically makes finding the next relevant document difficult, but Predict excelled with a low richness collection.
  2. This case involved OCR’d documents. Some people have suggested that TAR might not work well with OCR’d text but that has not been our experience. Predict worked well with this population.
  3. All documents were in Japanese. We have written about our success in ranking non-English documents but some have expressed doubt. This study again illustrates the effectiveness of Predict’s analytical tools when the documents are properly tokenized.

These experiments show that there are real, significant savings to using Predict, no matter the size, richness or language of the document collection.

Conclusion

Paul Simon, that great legal technologist, knew long ago that it was time to put an end to keywords and linear review:

The problem is all inside your head, she said to me.
The answer is easy if you take it logically.
I’d like to help you as we become keyword free.
There must be fifty-seven ways to leave your (linear) lover.

She said it’s really not my habit to intrude.
But this wasteful spending means your clients are getting screwed.
So I repeat myself, at the risk of being cruel.
There must be fifty-seven ways to leave your linear lover,
Fifty-seven ways to leave your (linear) lover.

Just slip out the back, Peck, make a new plan, Ralph.
Don’t need to be coy, Gord, just listen to me.
Hop on the bus, Craig, don’t need to discuss much.
Just drop the keywords, Mary, and get yourself (linear) free.

She said it grieves me so to see you in such pain.
When you drop those keywords I know you’ll smile again.
I said, linear review is as expensive as can be.
There must be fifty-seven ways ways to leave your (linear) lover.

Just slip out the back, Shira, make a new plan, Gord.
Don’t need to be coy, Joy, just listen to me.
Hop on the bus, Tom, don’t need to discuss much.
Just drop the keywords, Gayle, and get yourself (linear) free.

She said, why don’t we both just sleep on it tonight.
And I believe, in the morning you’ll begin to see the light.
When the review team sent their bill I realized she probably was right.
There must be fifty-seven ways to leave your (linear) lover.
Fifty-seven ways to leave your (linear) lover.

Just slip out the back, Maura, make a new plan, Fatch.
Don’t need to be coy, Andrew, just listen to me.
Hop on the bus, Michael, don’t need to discuss much.
Just drop off the keywords, Herb, and get yourself (linear) free.

 

[1] We chose to initiate the ranking using a single document simply to see how well Predict would perform in this investigation from the absolute minimum starting point. In reality, a Predict simulation can use as many responsive and non-responsive documents as desired. In most cases, we use the same starting point (i.e., the exact same documents and judgments) used by the client to initiate the original review that is being simulated.

[2] We chose to review twenty documents at a time because that is what we typically recommend for batch sizes in an investigation, to take maximum advantage of the ability of Predict to re-rank several times an hour.

[3] It is interesting to note that Predict did not find relevant documents as quickly using a non-relevant starting seed, which isn’t surprising. However, it caught up with the earlier simulation by the 70% mark and proved just as effective.

[4] Compositing the text of five responsive documents into one is a reasonable experiment to run. But it’s not what most people think of when they think synthetic seed. They imagine some lawyer crafting verbiage him- or herself, writing something up about what they expect to find, in their own words. And then using that document to start the training. Using the literal text of five documents already deemed to be responsive is not the same thing but it made for an interesting experiment.

Written by:

Association of Certified E-Discovery Specialists (ACEDS)
Contact
more
less

Association of Certified E-Discovery Specialists (ACEDS) on:

Readers' Choice 2017
Reporters on Deadline

"My best business intelligence, in one easy email…"

Your first step to building a free, personalized, morning email brief covering pertinent authors and topics on JD Supra:
*By using the service, you signify your acceptance of JD Supra's Privacy Policy.
Custom Email Digest
- hide

JD Supra Privacy Policy

Updated: May 25, 2018:

JD Supra is a legal publishing service that connects experts and their content with broader audiences of professionals, journalists and associations.

This Privacy Policy describes how JD Supra, LLC ("JD Supra" or "we," "us," or "our") collects, uses and shares personal data collected from visitors to our website (located at www.jdsupra.com) (our "Website") who view only publicly-available content as well as subscribers to our services (such as our email digests or author tools)(our "Services"). By using our Website and registering for one of our Services, you are agreeing to the terms of this Privacy Policy.

Please note that if you subscribe to one of our Services, you can make choices about how we collect, use and share your information through our Privacy Center under the "My Account" dashboard (available if you are logged into your JD Supra account).

Collection of Information

Registration Information. When you register with JD Supra for our Website and Services, either as an author or as a subscriber, you will be asked to provide identifying information to create your JD Supra account ("Registration Data"), such as your:

  • Email
  • First Name
  • Last Name
  • Company Name
  • Company Industry
  • Title
  • Country

Other Information: We also collect other information you may voluntarily provide. This may include content you provide for publication. We may also receive your communications with others through our Website and Services (such as contacting an author through our Website) or communications directly with us (such as through email, feedback or other forms or social media). If you are a subscribed user, we will also collect your user preferences, such as the types of articles you would like to read.

Information from third parties (such as, from your employer or LinkedIn): We may also receive information about you from third party sources. For example, your employer may provide your information to us, such as in connection with an article submitted by your employer for publication. If you choose to use LinkedIn to subscribe to our Website and Services, we also collect information related to your LinkedIn account and profile.

Your interactions with our Website and Services: As is true of most websites, we gather certain information automatically. This information includes IP addresses, browser type, Internet service provider (ISP), referring/exit pages, operating system, date/time stamp and clickstream data. We use this information to analyze trends, to administer the Website and our Services, to improve the content and performance of our Website and Services, and to track users' movements around the site. We may also link this automatically-collected data to personal information, for example, to inform authors about who has read their articles. Some of this data is collected through information sent by your web browser. We also use cookies and other tracking technologies to collect this information. To learn more about cookies and other tracking technologies that JD Supra may use on our Website and Services please see our "Cookies Guide" page.

How do we use this information?

We use the information and data we collect principally in order to provide our Website and Services. More specifically, we may use your personal information to:

  • Operate our Website and Services and publish content;
  • Distribute content to you in accordance with your preferences as well as to provide other notifications to you (for example, updates about our policies and terms);
  • Measure readership and usage of the Website and Services;
  • Communicate with you regarding your questions and requests;
  • Authenticate users and to provide for the safety and security of our Website and Services;
  • Conduct research and similar activities to improve our Website and Services; and
  • Comply with our legal and regulatory responsibilities and to enforce our rights.

How is your information shared?

  • Content and other public information (such as an author profile) is shared on our Website and Services, including via email digests and social media feeds, and is accessible to the general public.
  • If you choose to use our Website and Services to communicate directly with a company or individual, such communication may be shared accordingly.
  • Readership information is provided to publishing law firms and authors of content to give them insight into their readership and to help them to improve their content.
  • Our Website may offer you the opportunity to share information through our Website, such as through Facebook's "Like" or Twitter's "Tweet" button. We offer this functionality to help generate interest in our Website and content and to permit you to recommend content to your contacts. You should be aware that sharing through such functionality may result in information being collected by the applicable social media network and possibly being made publicly available (for example, through a search engine). Any such information collection would be subject to such third party social media network's privacy policy.
  • Your information may also be shared to parties who support our business, such as professional advisors as well as web-hosting providers, analytics providers and other information technology providers.
  • Any court, governmental authority, law enforcement agency or other third party where we believe disclosure is necessary to comply with a legal or regulatory obligation, or otherwise to protect our rights, the rights of any third party or individuals' personal safety, or to detect, prevent, or otherwise address fraud, security or safety issues.
  • To our affiliated entities and in connection with the sale, assignment or other transfer of our company or our business.

How We Protect Your Information

JD Supra takes reasonable and appropriate precautions to insure that user information is protected from loss, misuse and unauthorized access, disclosure, alteration and destruction. We restrict access to user information to those individuals who reasonably need access to perform their job functions, such as our third party email service, customer service personnel and technical staff. You should keep in mind that no Internet transmission is ever 100% secure or error-free. Where you use log-in credentials (usernames, passwords) on our Website, please remember that it is your responsibility to safeguard them. If you believe that your log-in credentials have been compromised, please contact us at privacy@jdsupra.com.

Children's Information

Our Website and Services are not directed at children under the age of 16 and we do not knowingly collect personal information from children under the age of 16 through our Website and/or Services. If you have reason to believe that a child under the age of 16 has provided personal information to us, please contact us, and we will endeavor to delete that information from our databases.

Links to Other Websites

Our Website and Services may contain links to other websites. The operators of such other websites may collect information about you, including through cookies or other technologies. If you are using our Website or Services and click a link to another site, you will leave our Website and this Policy will not apply to your use of and activity on those other sites. We encourage you to read the legal notices posted on those sites, including their privacy policies. We are not responsible for the data collection and use practices of such other sites. This Policy applies solely to the information collected in connection with your use of our Website and Services and does not apply to any practices conducted offline or in connection with any other websites.

Information for EU and Swiss Residents

JD Supra's principal place of business is in the United States. By subscribing to our website, you expressly consent to your information being processed in the United States.

  • Our Legal Basis for Processing: Generally, we rely on our legitimate interests in order to process your personal information. For example, we rely on this legal ground if we use your personal information to manage your Registration Data and administer our relationship with you; to deliver our Website and Services; understand and improve our Website and Services; report reader analytics to our authors; to personalize your experience on our Website and Services; and where necessary to protect or defend our or another's rights or property, or to detect, prevent, or otherwise address fraud, security, safety or privacy issues. Please see Article 6(1)(f) of the E.U. General Data Protection Regulation ("GDPR") In addition, there may be other situations where other grounds for processing may exist, such as where processing is a result of legal requirements (GDPR Article 6(1)(c)) or for reasons of public interest (GDPR Article 6(1)(e)). Please see the "Your Rights" section of this Privacy Policy immediately below for more information about how you may request that we limit or refrain from processing your personal information.
  • Your Rights
    • Right of Access/Portability: You can ask to review details about the information we hold about you and how that information has been used and disclosed. Note that we may request to verify your identification before fulfilling your request. You can also request that your personal information is provided to you in a commonly used electronic format so that you can share it with other organizations.
    • Right to Correct Information: You may ask that we make corrections to any information we hold, if you believe such correction to be necessary.
    • Right to Restrict Our Processing or Erasure of Information: You also have the right in certain circumstances to ask us to restrict processing of your personal information or to erase your personal information. Where you have consented to our use of your personal information, you can withdraw your consent at any time.

You can make a request to exercise any of these rights by emailing us at privacy@jdsupra.com or by writing to us at:

Privacy Officer
JD Supra, LLC
10 Liberty Ship Way, Suite 300
Sausalito, California 94965

You can also manage your profile and subscriptions through our Privacy Center under the "My Account" dashboard.

We will make all practical efforts to respect your wishes. There may be times, however, where we are not able to fulfill your request, for example, if applicable law prohibits our compliance. Please note that JD Supra does not use "automatic decision making" or "profiling" as those terms are defined in the GDPR.

  • Timeframe for retaining your personal information: We will retain your personal information in a form that identifies you only for as long as it serves the purpose(s) for which it was initially collected as stated in this Privacy Policy, or subsequently authorized. We may continue processing your personal information for longer periods, but only for the time and to the extent such processing reasonably serves the purposes of archiving in the public interest, journalism, literature and art, scientific or historical research and statistical analysis, and subject to the protection of this Privacy Policy. For example, if you are an author, your personal information may continue to be published in connection with your article indefinitely. When we have no ongoing legitimate business need to process your personal information, we will either delete or anonymize it, or, if this is not possible (for example, because your personal information has been stored in backup archives), then we will securely store your personal information and isolate it from any further processing until deletion is possible.
  • Onward Transfer to Third Parties: As noted in the "How We Share Your Data" Section above, JD Supra may share your information with third parties. When JD Supra discloses your personal information to third parties, we have ensured that such third parties have either certified under the EU-U.S. or Swiss Privacy Shield Framework and will process all personal data received from EU member states/Switzerland in reliance on the applicable Privacy Shield Framework or that they have been subjected to strict contractual provisions in their contract with us to guarantee an adequate level of data protection for your data.

California Privacy Rights

Pursuant to Section 1798.83 of the California Civil Code, our customers who are California residents have the right to request certain information regarding our disclosure of personal information to third parties for their direct marketing purposes.

You can make a request for this information by emailing us at privacy@jdsupra.com or by writing to us at:

Privacy Officer
JD Supra, LLC
10 Liberty Ship Way, Suite 300
Sausalito, California 94965

Some browsers have incorporated a Do Not Track (DNT) feature. These features, when turned on, send a signal that you prefer that the website you are visiting not collect and use data regarding your online searching and browsing activities. As there is not yet a common understanding on how to interpret the DNT signal, we currently do not respond to DNT signals on our site.

Access/Correct/Update/Delete Personal Information

For non-EU/Swiss residents, if you would like to know what personal information we have about you, you can send an e-mail to privacy@jdsupra.com. We will be in contact with you (by mail or otherwise) to verify your identity and provide you the information you request. We will respond within 30 days to your request for access to your personal information. In some cases, we may not be able to remove your personal information, in which case we will let you know if we are unable to do so and why. If you would like to correct or update your personal information, you can manage your profile and subscriptions through our Privacy Center under the "My Account" dashboard. If you would like to delete your account or remove your information from our Website and Services, send an e-mail to privacy@jdsupra.com.

Changes in Our Privacy Policy

We reserve the right to change this Privacy Policy at any time. Please refer to the date at the top of this page to determine when this Policy was last revised. Any changes to our Privacy Policy will become effective upon posting of the revised policy on the Website. By continuing to use our Website and Services following such changes, you will be deemed to have agreed to such changes.

Contacting JD Supra

If you have any questions about this Privacy Policy, the practices of this site, your dealings with our Website or Services, or if you would like to change any of the information you have provided to us, please contact us at: privacy@jdsupra.com.

JD Supra Cookie Guide

As with many websites, JD Supra's website (located at www.jdsupra.com) (our "Website") and our services (such as our email article digests)(our "Services") use a standard technology called a "cookie" and other similar technologies (such as, pixels and web beacons), which are small data files that are transferred to your computer when you use our Website and Services. These technologies automatically identify your browser whenever you interact with our Website and Services.

How We Use Cookies and Other Tracking Technologies

We use cookies and other tracking technologies to:

  1. Improve the user experience on our Website and Services;
  2. Store the authorization token that users receive when they login to the private areas of our Website. This token is specific to a user's login session and requires a valid username and password to obtain. It is required to access the user's profile information, subscriptions, and analytics;
  3. Track anonymous site usage; and
  4. Permit connectivity with social media networks to permit content sharing.

There are different types of cookies and other technologies used our Website, notably:

  • "Session cookies" - These cookies only last as long as your online session, and disappear from your computer or device when you close your browser (like Internet Explorer, Google Chrome or Safari).
  • "Persistent cookies" - These cookies stay on your computer or device after your browser has been closed and last for a time specified in the cookie. We use persistent cookies when we need to know who you are for more than one browsing session. For example, we use them to remember your preferences for the next time you visit.
  • "Web Beacons/Pixels" - Some of our web pages and emails may also contain small electronic images known as web beacons, clear GIFs or single-pixel GIFs. These images are placed on a web page or email and typically work in conjunction with cookies to collect data. We use these images to identify our users and user behavior, such as counting the number of users who have visited a web page or acted upon one of our email digests.

JD Supra Cookies. We place our own cookies on your computer to track certain information about you while you are using our Website and Services. For example, we place a session cookie on your computer each time you visit our Website. We use these cookies to allow you to log-in to your subscriber account. In addition, through these cookies we are able to collect information about how you use the Website, including what browser you may be using, your IP address, and the URL address you came from upon visiting our Website and the URL you next visit (even if those URLs are not on our Website). We also utilize email web beacons to monitor whether our emails are being delivered and read. We also use these tools to help deliver reader analytics to our authors to give them insight into their readership and help them to improve their content, so that it is most useful for our users.

Analytics/Performance Cookies. JD Supra also uses the following analytic tools to help us analyze the performance of our Website and Services as well as how visitors use our Website and Services:

  • HubSpot - For more information about HubSpot cookies, please visit legal.hubspot.com/privacy-policy.
  • New Relic - For more information on New Relic cookies, please visit www.newrelic.com/privacy.
  • Google Analytics - For more information on Google Analytics cookies, visit www.google.com/policies. To opt-out of being tracked by Google Analytics across all websites visit http://tools.google.com/dlpage/gaoptout. This will allow you to download and install a Google Analytics cookie-free web browser.

Facebook, Twitter and other Social Network Cookies. Our content pages allow you to share content appearing on our Website and Services to your social media accounts through the "Like," "Tweet," or similar buttons displayed on such pages. To accomplish this Service, we embed code that such third party social networks provide and that we do not control. These buttons know that you are logged in to your social network account and therefore such social networks could also know that you are viewing the JD Supra Website.

Controlling and Deleting Cookies

If you would like to change how a browser uses cookies, including blocking or deleting cookies from the JD Supra Website and Services you can do so by changing the settings in your web browser. To control cookies, most browsers allow you to either accept or reject all cookies, only accept certain types of cookies, or prompt you every time a site wishes to save a cookie. It's also easy to delete cookies that are already saved on your device by a browser.

The processes for controlling and deleting cookies vary depending on which browser you use. To find out how to do so with a particular browser, you can use your browser's "Help" function or alternatively, you can visit http://www.aboutcookies.org which explains, step-by-step, how to control and delete cookies in most browsers.

Updates to This Policy

We may update this cookie policy and our Privacy Policy from time-to-time, particularly as technology changes. You can always check this page for the latest version. We may also notify you of changes to our privacy policy by email.

Contacting JD Supra

If you have any questions about how we use cookies and other tracking technologies, please contact us at: privacy@jdsupra.com.

- hide

This website uses cookies to improve user experience, track anonymous site usage, store authorization tokens and permit sharing on social media networks. By continuing to browse this website you accept the use of cookies. Click here to read more about how we use cookies.