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.

  • Teleco.IO
    Teleco.IO offers an API for telecommunications services to help manage their industry. The API allows asset management and reporting, enabling providers to search, order, and provision their telecom assets throughout an entire data lifecycle across multiple networks. Currently in a private beta, interested parties can request API access from the Teleco.IO website. Date Updated: 2014-12-19 […]
  • Inquiry
    Open311 allows developers to create third-party apps to report and view citizen neighborhood issues such as potholes to graffiti and more using a city's 311 reporting system. Now on version 1, the RESTful Inquiry API is the tool used to query the 311 database. HTTP GET calls can be sent to the API to list […]
  • Clearent
    Clearent is an integration tool for eCommerce, combining sites, shopping carts, mobile interfaces, payment processing, and Point of Sale applications to create comprehensive payment-enabled eCommerce applications. The API is compatible with shopping carts such as ZenCart, OpenCart, OSCommerce, and custom user applications. Using the Clearent API, providers can process sales, authorizations, captures, refunds, and voids. […]
  • Google Enterprise License Manager
    Located within the Admin SDK, the Google Enterprise License Manager API enables enterprise developers to programmatically manage their licenses. The API can be used to revoke a license, return a specific user's licensee by inputted product SKU, create and assign licenses, list all licenses associated with a specific product, and reassign SKUs with licenses. The […]
  • FT Headline
    Financial Times is a business intelligence service that extracts vital information critical to business news. The FT Headline API enables developers to create a newsfeed of relevant real time business news for integration into 3rd party websites or applications. These headlines can be ported into existing CRM, newsletters, and information portals. Date Updated: 2014-12-16 Tags: […]
  • migme
    migme is a social media service that offers chat, microblogging, and entertainment integrations to increase monetization through marketing and user onboarding. The RESTful migme API allows access to it's 9 million user base, enabling programmatic social media functionality, such as the acquisition of comprehensive user profile information, and the ability to invite friends, make a […]
  • Yes or No
    The simple Yes or No API is made for automating boolean decision making within mobile environments. API calls will return a "Yes", "No" or "Maybe." Returns include fun links to comical Gifs, such as Hugh Laurie or Client Eastwood nodding in approval, or Jim from the Office excitedly mouthing "Yes!", or an uncomfortably slow camera […]
  • W3C Vibration
    The Vibration API is a simple browser-based device API documented by the W3C Device APIs Working Group. The Vibration API enables developers to trigger the vibration mechanism in a hosting device, such as a smartphone. The vibration length and pattern of the vibrations can be customized. The API offers simple tactile feedback, not fine-grained control. […]
  • W3C Battery Status
    The Battery Status API, documented by W3C, is a browser-based API that enables web developers to discover the battery life of a hosting device. This enables web application features to be dynamically catered to a device's battery status, improving power-efficiency and user experience. The API dependences include EcmaScript and WebIDL version 2. The Battery Status […]
  • DOJ Law Jobs
    The U.S. Department of Justice (DOJ) Law Jobs API distributes available government legal job openings and vacancy announcements, sourced from the Office of Attorney Recruitment and Management. This digital distribution channel exists to make job openings more transparent to the public. This API is also the main data source for the DOJ law jobs mobile […]