Posts Tagged ‘sentimentanalysis’

Stock Picker Shows the Potential of Leading Indicator Pattern

A recent blog over at MIT’s Technology Review site caught my attention. Who wouldn’t read a post when the title promises “AI That Picks Stocks Better than the Pros”? I was expecting to learn about cutting-edge research into neural networks or some such, but instead I found a description of an approach I have been pitching for years now.

The “Arizonal Financial Text System” (AZFinText) works by “ingesting large quantities of financial news stories (in initial tests, from Yahoo Finance) along with minute-by-minute stock price data, and then using the former to figure out how to predict the latter”. The stories get a unique type of sentiment-analysis treatment, which was written by AZFinText’s authors, Robert P. Schumaker of Iona College in New Rochelle and and Hsinchun Chen of the University of Arizona. (more information can be found in their IEEE paper)

As you might expect, “Bad” stories can be expected to make a stock go down, while “Good” stories can make it go up. But what differs with Schumaker and Chen’s approach is that they did not use traditional human gauges of sentiment. Rather than look for emotionally weighted words like hate, love, good, or bad used in a typical sentiment analysis technique (yes, I am oversimplifying the process greatly), they back-tested the moves in a stock’s price against historical stories and used that data to derive the words that seemed to influence movement. This uncovered terms like hereto, comparable, charge, summit and green which caused the stock to move down, while words like planted, announcing, front, smaller and crude triggered an increase.

Before I explain my similar experiments in this area using mashups, I should point out that the basic idea here is nothing new. The article sites research in this area going back at least to 1990.

In my book, I describe applying mashups to this problem in my explanation of the Leading Indicator pattern:

Changes in a leading indicator may foretell downstream impact in other areas. Some, like the measurement of new home sales or bankruptcy filings have an obvious affect on many businesses. Well- known leading indicators do not offer any particular competitive advantage. Finding previously unknown relationships that predict business cycles and trends can be extremely useful.

Schumaker and Chen used Yahoo News stories in their study. But of course, the more data you use, the more onerous the collection problem becomes. As I noted in Mashup Patterns:

The key to uncovering these hidden links begins with collecting Time Series data from multiple locations. But with each additional source that is surveyed, the complexity of the data gathering process increases.

I also describe how collecting this data is applicable for discovering both Leading and Coincident Indicators. For example:

…knowledge of the week’s upcoming television schedule might not seem useful for a chain of pet stores. But when matched against a set of key words, a time series of “pet-themed” broadcasts can be assembled. Mashed up against a database of customer purchases, a Leading Indicator might emerge between Dog Shows and increased sales. The retailer now has a mechanism for advance inventory and advertising planning.

But before this post “goes to the dogs”, let’s get back to the Technology Review article. The reason it really stuck with me is because I had already demonstrated working implementations. About a year ago, I was invited to speak with several hedge funds, and for two of them I demonstrated a mashup that used the New York Times news API along with Reuter’s Open Calais to forecast stock fluctuations.

Although it is not noted how Schumaker and Chen got their data from Yahoo, using the data collection capabilities of many mashup products (for example, Kapow, Convertigo, or Connotate) are an excellent source for your own Leading Indicator implementation.

The key challenge is to stop thinking about external business sites from a consumer’s perspective and instead view them as databases to be mined via periodic data extraction. Here’s a final example from the Leading Indicator chapter that I know at least two firms have actually implemented:

Consider the value of building a mashup against popular online travel sites. Each day, an automated agent could book multiple flights between New York and London and from Boston to San Francisco. The mashup emulates the customer booking experience all the way up through seat selection, at which point it records the number of seats available and the ticket price. Naturally, the mashup wouldn’t complete the process of paying for the trip.

This information can be used to extrapolate the performance of the sector in advance of quarterly reports. Lots of seats available even as ticket prices decline? Probably not a sign of good earnings. Regularly filled seats at soaring prices might seem like good news until a time series of fuel prices hitting historical highs is added.

AZFinText operates on an extremely tight window of time, according to the article. It attempts to find stories that will move a stock within the next 20 minutes or so. This means that to be of practical use, it probably needs to be part of an automated trading system. But I hope the other examples I’ve shown demonstrate that larger timeframes can be involved and there can be plenty of time for actual people to evaluate the results and decide on a course of action. The Leading Indicator pattern might help you get information that your competitors don’t have. Or if they will have it eventually, you can at least get this knowledge before they do.

  • TripAdvisor Content
    TripAdvisor is one of the world's largest travel sites featuring reviews and advice on hotels, resorts, flights, vacation rentals, vacation packages, travel guides, and more. TripAdvisor's Content API allows access to business information on travel destinations. API calls can be made using HTTP requests to return data in JSON formats. The API retur […]
  • Health Topics. Net
    Health Topics .Net is an unofficial API that displays health information from recognized sources in English and Spanish. To know more about this application, developers can either access a live preview or a screenshot. This API could be valuable for developers in bilingual markets who work with health related applications. To start, users could register at c […]
  • Time and Date Dialing Codes Service
    With Time and Date users can access time zones, calendars, weather, the world clock and astronomy information. They can also obtain free clocks, free countdowns and APIs. Time and Date Dialing Codes Service API can be used to find out which code serves better to call a specific location. To start application development, developers can review some of the rec […]
  • CenturyLink
    CenturyLink is a telecommunications company that offers cloud services for business, development, SaaS and resellers. The company offers an API that supports REST based HTTP requests in XML, JSON and SOAP protocols. The goals are to display billing, data centers, network usage, upcoming events and activity log. This API may serve as a control portal and coul […]
  • F5
    F5 is an IT company that improves network security. Some of the solutions include networks functions virtualization, secure web gateway and cloud migration. Products involve platforms, modules, BIG-IP and BIG-IQ device, cloud and security. To access more information developers can visit the link iControl CodeShare, where they will have access to iControlREST […]
  • Time and Date Places
    Time and Date Places API can retrieve names of places geographically identified in a list. Recognized parameters include geo and lang and response elements consist of places. Developers can find examples in XML/JSON formats. This API about places can be useful for developers who want to locate information related to a country, a state, latitude and longitude […]
  • The Portal to Texas History
    The Portal to Texas History is a resource to learn about past events occurred in Texas. The organization offers APIs for the Corpus Cristi Museum of Science and History and invites developers to access data without a special key. They can benefit from this API if they are interested to organize databases with science and history content. In addition, develop […]
  • Badips
    Badips.com is a free abuse tracker and IP monitoring community offering a way to report and compile blocklists of bad IPs. With an API key, developers can access Badips.com through a simple HTTP request RESTful API to receive a list of bad IPs along with specific individual IP information. Developers are also open to make a POST method to add new IPs to add […]
  • Time and Date Holidays
    Time and Date Holiday Service API displays a list of observances for over 70 countries. With this API, developers can retrieve holiday name and date, type of holiday and short description of the holiday. They also can access holiday information of the states in the country that observe the holiday. This API could be useful if the goal is to integrate observa […]
  • Time and Date Daylight Saving Time (DST) Worldwide
    With Daylight Saving Time Worldwide API, developers can manage dates, times and zone changes in multiple countries. This service is featured in Time and Date, a company based in Norway that informs users about the world clock, calendars, weather, astronomy and time zones. Particularly with this company, developers can create applications at no cost, but if t […]