Data Analytics
Our expert investigators use specialized computer software to review files, hard drives and email analytics,
social media, cell phone and cloud data to ensure no information is missed.
Our eDiscovery software capabilities are unlike that of any other discovery support company, and with our “best of the breed” technology and online repository services, you can securely access your case files and discovery production from anywhere in the world.
At ILS, technology provides the edge that helps us balance against the overwhelming resources that battling BigLaw defense requires. We use a number of best of breed tools, but we’ve also enhanced some of those and created others to solve Plaintiff specific needs. In short, we have a very robust, fully functional, technology infrastructure that leverages the best of Artificial Intelligence. However, we maintain that it isn’t the tools you have, but how you use them.
All TAR tools have strengths and weaknesses. In order to properly use the tools, one has to understand what they can and cannot do. Importantly, results always need to be validated. It is just as important to test the discarded documents as it is to classify those first identified. Most defense-oriented providers are focused on the culling properties of TAR. They are adept at elimination. Machine learning can be a powerful tool, but it is taught how to decide by humans. We want to assure that defendants don’t allow their implicit bias to teach the system in a manner detrimental to Plaintiffs, which we address with negotiation of an effective ESI Protocol. Having ILS by your side to assure the agreements you make are beneficial, can have a greater impact on the outcome than effective Vior Dire.
Our eDiscovery software capabilities are unlike that of any other discovery support company, and with our “best of the breed” technology and online repository services, you can securely access your case files and discovery production from anywhere in the world.
At ILS, technology provides the edge that helps us balance against the overwhelming resources that battling BigLaw defense requires. We use a number of best of breed tools, but we’ve also enhanced some of those and created others to solve Plaintiff specific needs. In short, we have a very robust, fully functional, technology infrastructure that leverages the best of Artificial Intelligence. However, we maintain that it isn’t the tools you have, but how you use them.
All TAR tools have strengths and weaknesses. In order to properly use the tools, one has to understand what they can and cannot do. Importantly, results always need to be validated. It is just as important to test the discarded documents as it is to classify those first identified. Most defense-oriented providers are focused on the culling properties of TAR. They are adept at elimination. Machine learning can be a powerful tool, but it is taught how to decide by humans. We want to assure that defendants don’t allow their implicit bias to teach the system in a manner detrimental to Plaintiffs, which we address with negotiation of an effective ESI Protocol. Having ILS by your side to assure the agreements you make are beneficial, can have a greater impact on the outcome than effective Vior Dire.
Continuous Active Learning (CAL) is great for defendants and symmetrically situated opposing parties. It avoids having a subject matter expert teaching the system and instead, utilizes a regular contract review team whose decisions ultimately determine what gets produced. The system enriches review batches based on similarity with prior responsiveness calls and enables the review to cease before all documents have been “eyes on” reviewed. The review is based on instructions from defense counsel and often contains the implicit bias held by the defense team. But what if the same bias is internalized by those low paid contract reviewers? Their decisions will teach the computer to find more like what the reviewers have identified as responsive. With slight tweaking, the machine learning system may be RIGGED against Plaintiffs. As usual, the devil is in the details. With ILS on your side, we’ll help you make the arguments to assure that the process is balanced.
Also, in applying TAR, defendants want the maximum precision. They don’t want to produce any borderline or extraneously responsive documents. Precision is the percentage of retrieved documents that are relevant. Recall is the percentage of relevant documents that are retrieved – that’s what Plaintiffs want. A high precision number is focusing on a subset and ignoring the larger context of the document population. TAR could retrieve a fraction of the relevant documents and still have a high precision score, even though there were substantially more documents that weren’t found than were scored in the calculation.
But for documents that are produced, particularly in large volumes, the key to using TAR is in classifying and categorizing what has been produced into usable issues. This is ILS’ sweet spot. The analysis. Using AI to determine if there are custodians who seem to play a bigger role than their data volume would suggest indicating that there may be missing custodians. Examining the data volume chronologically to determine if there are data gaps around key events; examining social networks with 6 Degrees® Visualization; and conducting a search term optimization exercise based on real data to augment search methodology. And using the Find More Like functionality to parse the database for other documents on the same are of interest. ILS will facilitate this level of investigation. Again, its not the tools per se, it’s the way they are applied. For Plaintiff-Only discovery, our focus is on using TAR tools to characterize what was produced. It’s a different mindset.
Also, in applying TAR, defendants want the maximum precision. They don’t want to produce any borderline or extraneously responsive documents. Precision is the percentage of retrieved documents that are relevant. Recall is the percentage of relevant documents that are retrieved – that’s what Plaintiffs want. A high precision number is focusing on a subset and ignoring the larger context of the document population. TAR could retrieve a fraction of the relevant documents and still have a high precision score, even though there were substantially more documents that weren’t found than were scored in the calculation.
But for documents that are produced, particularly in large volumes, the key to using TAR is in classifying and categorizing what has been produced into usable issues. This is ILS’ sweet spot. The analysis. Using AI to determine if there are custodians who seem to play a bigger role than their data volume would suggest indicating that there may be missing custodians. Examining the data volume chronologically to determine if there are data gaps around key events; examining social networks with 6 Degrees® Visualization; and conducting a search term optimization exercise based on real data to augment search methodology. And using the Find More Like functionality to parse the database for other documents on the same are of interest. ILS will facilitate this level of investigation. Again, its not the tools per se, it’s the way they are applied. For Plaintiff-Only discovery, our focus is on using TAR tools to characterize what was produced. It’s a different mindset.
Targeting the issues important to your case
In our experience, less than 10 percent of defense production is relevant to the issues important to the Plaintiffs. Yet, to get to that 10 percent, a traditional document review process will require your team to spend many months (and obscene amounts of money) to pore through the production looking for the relevant documents.
Instead of the traditional brute force review process, ILS uses “Expert Systems” to programmatically and accurately issue code defense produced sets of electronic documents. Our litigation consultants train sophisticated AI-based document analytics to recognize your key issues. Our systems then “read” through and analyze enormous volumes of documents identifying the data you want to read – the documents which are highly relevant to the topics that you need to work your case. Your review team can spend its time focusing on the 10 percent of the documents that are meaningful to your case, rather than getting bogged down in the 90 percent that will not matter.
Instead of the traditional brute force review process, ILS uses “Expert Systems” to programmatically and accurately issue code defense produced sets of electronic documents. Our litigation consultants train sophisticated AI-based document analytics to recognize your key issues. Our systems then “read” through and analyze enormous volumes of documents identifying the data you want to read – the documents which are highly relevant to the topics that you need to work your case. Your review team can spend its time focusing on the 10 percent of the documents that are meaningful to your case, rather than getting bogged down in the 90 percent that will not matter.
Furthermore, we can complete this in a matter of weeks, not the months or years required for traditional document review. Our process also has a high accuracy rating – much higher than can be accomplished through a traditional human review process.
Our Automated Issue Coding process is multi-lingual, so Chinese, Japanese, Korean, German, Russian, and many more languages are analyzed for issue relevancy with ease!
Our Automated Issue Coding process is multi-lingual, so Chinese, Japanese, Korean, German, Russian, and many more languages are analyzed for issue relevancy with ease!
Understanding Data
Understanding, classifying and organizing the evidence that’s produced to fulfill each element of your cause of action. That’s the ultimate goal of discovery from the Plaintiff’s perspective. Which are the hot docs needed for deposition or trial? Who are the relevant or key custodians or entities? Who did what and when? What did they know and when did they know it? Whose deposition should we take, and in what order? Is there evidence of spoliation? And, if there are foreign language documents, how do I even identify them and what do they say? Applying the best in class tools, ILS Analytics helps you answer all these questions faster and with more precision.
Instead of the traditional brute force review process, ILS uses advanced analytical tools and proven methodologies to programmatically organize and reveal patterns within a production not readily apparent from manual linear review.
Instead of the traditional brute force review process, ILS uses advanced analytical tools and proven methodologies to programmatically organize and reveal patterns within a production not readily apparent from manual linear review.
Our systems “read” through and analyze enormous volumes of documents identifying the data you want to focus on – the documents which are most relevant to the topics in your case so that your review team can spend its time focusing on the 10 percent of the documents that are meaningful, rather than getting bogged down on the 90 percent that are duplicative, redundant, marginally responsive or simply were produced in an attempt to hide the relevant needles in a larger haystack..
Furthermore, we can complete this process quickly, not the months or years required for traditional document review. This is critical when a defendant has dumped tens or hundreds of thousands of documents on the eve of a deposition or you have a tight court ordered discovery cut-off deadline looming but have yet to really start your document review. ILS manages cases with 10’s of millions of documents and we know how to handle data dumps.
Furthermore, we can complete this process quickly, not the months or years required for traditional document review. This is critical when a defendant has dumped tens or hundreds of thousands of documents on the eve of a deposition or you have a tight court ordered discovery cut-off deadline looming but have yet to really start your document review. ILS manages cases with 10’s of millions of documents and we know how to handle data dumps.