Quantitative Legal Prediction and You

When one thinks of the practice of law, I imagine one thinks “qualitative”, relegating the “quantitative” to the accountants and actuaries. But the more data we can collect and mine, the more likely even the most judgment-based tasks can be influenced by trends. That is the premise behind the label “quantitative legal prediction” – mining “big data” for trends in legal decisions and court filings, statutory evolution and legal billing and task performance in order to predict outcomes. The ABA Journal reports on an article at Law Technology News  touching on the concept and how it is being used in a few scenarios. How could this work? Imagine crawling the opinions and decisions in Pacer to find the arguments that supported the most winning results? While the key to the effectiveness of the tech is getting the information into mine-able form, there are already services and firms making inroads. There are programs for e-discovery using algorithms to identify documents most likely to be relevant to a given discovery request. Ty-Metrix, a legal billing software, has collected massive amounts of billing data and can now mine it for law firm rates and the factors that affect those rates. Then there is Lex Machina, an organization that has spent 10 years trying to build and organize an effective database for intellectual property litigation.

There are other examples as well in the LTN article. And the article and its examples herald for me an era in law practice that I have been eagerly anticipating – that moment when we can dip into all the available information on a given subject, tap the data and return predictive answers back using an interface like Wolfram Alpha. I don’t believe that this ability means the death of human judgment. Quite the opposite – armed with better data, more complete information, our judgment will be sharpened and improved. I welcome our Big Data Driven overlords and their semantic minions. It will be interesting to see what the next few years brings, especially if efforts to demolish the PACER pay wall come to fruition.

Everything You Ever Wanted to Know About Internet Searching …

… or at least a great deal of it may be found in the pages of this “book” brought to you by the fine peeps at MakeUseOf. The 39-page PDF, aptly named “Guidebook To Internet Searching“, includes tips and tools for this increasingly-important skill. The book is broken down into sections devoted to the major search players and more esoteric tools by topic, such as searching for people, products, images, video, files, real time, and everyone’s favorite computational engine, Wolfram / Alpha. I love the Google search “cheat sheet” at the end, with lots of search terminology. Also, check out some of the other great Guidebooks they list at the back.

I bet there is something in here that will be new to you!

Hat tip to Jane’s e-Learning Tip Of The Day

Computational Search and Your Retirement


Image via Wikipedia

Still wondering what to do with computational search engine WolframAlpha? How about calculating your retirement? Sure you get those statements every year from social security, but why not get an answer that takes into account your current investment strategy, and shows your retirement projections with nifty charts, graphs and distribution comparisons. Check out the WA blog entry on it here and check out the calculator here.

Related articles by Zemanta:
Reblog this post [with Zemanta]

Why Just Search, When You Can Custom-Search?

Google, Bing, Ask, Hakia, Wolfram Alpha – nice information gathering tools to be sure, but do they really target exactly what you want you are looking for?

An often-overlooked option is creating a custom search engine that hones in on the sites and searches that you are most interested in. John DiGilio discusses the custom search engine option at LLRX in his article Bridging the DiGital Divide: Custom Search Engines Put You In Control.

DiGilio discusses two options: Google Custom Search and Rollyo (“Roll Your Own”) and mentions a third, CSE Links.

These tools allow you to direct your search at specific sites, include specific parameters and, essentially, cut loose the extraneous from your results. I have created a Google Custom Search engine that targets the websites of State Insurance Departments and related agencies and organizations, which is particularly useful for finding form filings and legislative news. I have compared results on my custom search site to general Google results and find the former more tailored and on-point.

If you find yourself searching the same issues over and over again and have specific results in mind, consider the custom search option and tap into that “do-it-yourself” aesthetic.

Reblog this post [with Zemanta]

Wolfram Alpha – Already Getting Bigger & Better

Less than a month old, the newborn Alpha is already celebrating by giving a gift back to its users: upgrades! Resource Shelf (and lots of others) report on the upgrades here. Resource Shelf quotes the changes reported on the Wolfram Alpha blog, and I requote them here for convenience:

Additional linguistic forms for many types of data and questions

More comparisons of composite properties (e.g. “US military vs. UK”)

Combined time series plots of different quantities (e.g. “germany gdp vs population”)

More complete handling of government positions (e.g. “chancellor”, etc.)

Updates to country borders for India, China, Slovenia, Croatia, and others

Updates to naming for certain politically sensitive countries and regions

Additional subcountry regions (e.g. “Wales”); many more to come

Additional support for current and past fractional timezones (e.g. “Iran time”)

City-by-city handling of U.S. states with multiple timezones

Updates to certain European currencies (e.g. for “Cyprus” and “Slovakia”)

Some additional historical events; many more to come

Additional probability computations for cards and coins (e.g. “2 or 3 aces”)

Additional output for partitions of integers (e.g. “partitions of 47″)

Implicit handling of geometric figure properties (e.g. “ellipse with area 6 and major axis 2″)

Additional support for Mathematica 3D graphics syntax

Additional support for stock prices with explicit dates

Support for planet-to-planet distances and “nearest planet”, etc.

Extra information when comparing incompatible units (e.g. “ergs vs. newtons”)

Improved linguistic handling for many foods (e.g. “love apple”)

More mountains added, especially in Australia

Support for many less-common given names (e.g. “zebulon”)

More “self-aware” questions answered (e.g. “how old are you”)

More consistent handling of sidebar links to Wikipedia, etc.

Happy Birthday to us!

[Caption]

Reblog this post [with Zemanta]

Google Squared – Structured Data Without The Human Touch

In another attempt to meet Wolfram Alpha head-on, Google has ushered in another “search” option: Google Squared. Squared collects unstructured data and automatically imposes a structure on it. Search results are pulled from various open sources and are organized in a spreadsheet-type format. Hovering over the cells will reveal the source.

A primary difference between Alpha and Squared is the lack of human oversight in the latter option: squares are automatically generated without human “curatorship.” Another weakness appears to be an overweening reliance on Wikipedia, with all its foibles and faults.

However, for a quick, chart-like presentation of data on a particular topic, Squared offers a nice alternative. Check out this “square” for smartphones (took about 15 seconds to generate) here. The smartphone square automatically created columns for image, description, weight, size and memory. Note that not all cells are complete – ostensibly because Squared couldn’t locate the unstructured data. I also note that generalized categories can yield results that may be too broad and require some tailoring. Familiar territory, for sure, when it comes to searching on any engine.

You can save your squares under your Google log in. You also can manually add items to Squares – good for comparison purposes.

Welcome to Google Squared, another tool to consider for inclusion in your search tool box (or bar)!

Hat tip to Resource Shelf.

Reblog this post [with Zemanta]

Firefox Handles the Wolfram Alpha / Google Debate with its own Negotiated Option

Leave it to Firefox to come up with a way to have your cake and eat it too. Amidst the hue and cry over the last few weeks surrounding the announcement and deployment of Alpha’s computational knowledge-based search engine and whether it would topple Google from its thrown (a decidedly red-herring-esque question), Lifehacker reports on a new Firefox extension that embeds Wolfram Alpha results into your Google search results page. Author Kevin Purdy advises that the experimental Firefox extension is a bit glitchy and haphazard. Nonetheless, Purdy is correct that the extension is worth trying because “getting a second, nerdier opinion from Wolfram Alpha is just what you needed in some cases.”

Reblog this post [with Zemanta]

Will Microsoft Build a Better Magnifying Glass?

Not to be outdown by the likes of Google and Wolfram Alpha, Microsoft appears to be unveiling its new search engine next week at the Wall Street Journal’s D: All Things D tech conference in Carlsbad, California, according to Resource Shelf.

The engine’s code name is Kumo, but it is really a rebranding of Microsoft Live Search conjoined with its new semantic ally, Powerset. And guess what? It is going to help us find more relevant results! The screenshots over at All Things Digital / Boomtown show a clean, spare look. PC World reports a three-column search results page with useful tools like related searches, a “single-session search history for quick backtracking”, and other related categories tied to your search inquiry. PC World uses an example of searching for a recording artist with results that include song lyrics, tickets, albums and the artist’s biography. Or searching for a product with results including images, reviews and product manuals.

Will Kumo stand or fall amidst the search stars? Not sure, but I can say this: more semantic competitors add up to us edging closer to a truly semantic on-line world! Kudos to Kumo!!!!

Reblog this post [with Zemanta]

Alpha’s Not Beta (Anymore)

Have you been hankering to try Wolfram Alpha’s new computational, knowledge-based search engine? Are you wondering if it is the next best thing in search? Well, I am playing with it right now, in another tab, and I have my own impressions.

For those who are still unsure of what Wolfram Alpha is, you can get the long, broad and sweeping answer at their “about” page. The short answer is that it is a search engine that “computes” answers for you by accessing a knowledge base treated or overlayed with algorithms / coding that Alpha can easily “read”. Or, if you ask Alpha this question “wolfram alpha”, you get this:

wolfram alpha

If you click on the “use as an internet domain link” on the above page, you get this:

Wolfram Alpha domain

I am fascinated with this new form of search interaction. But it is not the quick and dirty search service that Google offers and any comparison should end with the fact that they are both described as “search engines.” First, it takes some time to load the search page, much longer than it takes to load a Google page. Then it takes much longer to get an answer to your search inquiry, but that is expected. Alpha is not merely responding to your “query” with a list of pages ranked by hits. It is actually computing your answer by dipping into its information resources and providing a calculated response. The plus side is that you can be assured that your answer is most likely correct (unlike Google where the only assurance is that your answer has been hit by tens of thousands of other searchers).

The downside is that you have to consider whether Alpha is the best source for the particular information you are looking for and then you have to be very careful how you phrase your query. Take a look at Alpha’s search tips box:

Wolfram Alpha Help Tips

Alpha is great for quantitative questions, but not so good for qualitative questions. And even for quantitative questions, you have to be careful how you pose them. Talking to Alpha is much like talking to Spock – you will be treated to literal logic that is responsive to your request but may not be what you were looking for.

For example, my first search query was “distance from earth to sun.” Alpha got hung up on the words “distance” and “sun.” It defaulted on distance to astronomical units (AU) – how was Alpha to know that I meant miles? It did default to our Sun, but not before noting that it could not be sure that our Sun is what I meant. Fair enough.

I then asked it for “miles from earth to sun.” No answer. I then entered “miles from earth to sol.” No answer. I then entered “earth to sol” and, voila, I got astronomical units, kilometers, meters and miles. I also got a “corresponding quantity” of 4.5 micropascals, with an equation for how to get this amount.

When I finally got my answer, I got everything I was looking for and more. No question that my answer was accurate and scientifically solid. But getting there is more than half the battle and it helps to throw any notions about how to search in the more traditional formats right out the window.

Wolfram Alpha now has its place in my search arsenal – I added it to my Firefox search bar tool. But I will not be turning to Alpha for answers on every query. No doubt Alpha will evolve and will become more powerful as more information is made accessible to it. Give it a try yourself – I would love to hear about your impressions and results!

Reblog this post [with Zemanta]

Alpha's Not Beta (Anymore)

Have you been hankering to try Wolfram Alpha’s new computational, knowledge-based search engine? Are you wondering if it is the next best thing in search? Well, I am playing with it right now, in another tab, and I have my own impressions.

For those who are still unsure of what Wolfram Alpha is, you can get the long, broad and sweeping answer at their “about” page. The short answer is that it is a search engine that “computes” answers for you by accessing a knowledge base treated or overlayed with algorithms / coding that Alpha can easily “read”. Or, if you ask Alpha this question “wolfram alpha”, you get this:

wolfram alpha

If you click on the “use as an internet domain link” on the above page, you get this:

Wolfram Alpha domain

I am fascinated with this new form of search interaction. But it is not the quick and dirty search service that Google offers and any comparison should end with the fact that they are both described as “search engines.” First, it takes some time to load the search page, much longer than it takes to load a Google page. Then it takes much longer to get an answer to your search inquiry, but that is expected. Alpha is not merely responding to your “query” with a list of pages ranked by hits. It is actually computing your answer by dipping into its information resources and providing a calculated response. The plus side is that you can be assured that your answer is most likely correct (unlike Google where the only assurance is that your answer has been hit by tens of thousands of other searchers).

The downside is that you have to consider whether Alpha is the best source for the particular information you are looking for and then you have to be very careful how you phrase your query. Take a look at Alpha’s search tips box:

Wolfram Alpha Help Tips

Alpha is great for quantitative questions, but not so good for qualitative questions. And even for quantitative questions, you have to be careful how you pose them. Talking to Alpha is much like talking to Spock – you will be treated to literal logic that is responsive to your request but may not be what you were looking for.

For example, my first search query was “distance from earth to sun.” Alpha got hung up on the words “distance” and “sun.” It defaulted on distance to astronomical units (AU) – how was Alpha to know that I meant miles? It did default to our Sun, but not before noting that it could not be sure that our Sun is what I meant. Fair enough.

I then asked it for “miles from earth to sun.” No answer. I then entered “miles from earth to sol.” No answer. I then entered “earth to sol” and, voila, I got astronomical units, kilometers, meters and miles. I also got a “corresponding quantity” of 4.5 micropascals, with an equation for how to get this amount.

When I finally got my answer, I got everything I was looking for and more. No question that my answer was accurate and scientifically solid. But getting there is more than half the battle and it helps to throw any notions about how to search in the more traditional formats right out the window.

Wolfram Alpha now has its place in my search arsenal – I added it to my Firefox search bar tool. But I will not be turning to Alpha for answers on every query. No doubt Alpha will evolve and will become more powerful as more information is made accessible to it. Give it a try yourself – I would love to hear about your impressions and results!

Reblog this post [with Zemanta]