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.

  • Interactive Chart
    Markit on Demand's Interactive Chart API is for displaying the historical value of a company’s stock. The response contains end-of-day historical price information for companies traded on the BATS Exchange in the U.S. The response can include datasets containing open-high-low-close (OHLC) values, volume, Simple Moving Average (SMA), labeling helpers, co […]
  • Uber
    Using the Uber API, developers can integrate the power of Uber into 3rd party applications. Calls to the API can be made to request information on available car types, driver location expressed in geo-coordinates, time estimates, estimated prices (including currency conversion when applicable), as well as user account history and activity. The Uber API docum […]
  • Company Lookup
    Markit on Demand's Company Lookup API is used for finding the stock ticker or symbol a company’s stock is traded with. The API response includes the company’s symbol, its full name, and the exchange it’s traded on. Date Updated: 2014-08-20 Tags: [field_primary_category], [field_secondary_categories] […]
  • Product Hunt
    Product Hunt is a service that helps a user discover new apps, tech creations, hardware, and even job listings. Their website allows a user to login to add products and use an upvote system to rank products and showcase new trends. Their API, currently in sign-up phase, will allow developers to access their data on file to create 3rd party applications and w […]
  • Omega Ricochet
    RacoWireless offers a collection of communication management tools with their DevCloud and Omega Management Suite. The platform is designed to increase interoperability between IoT devices with RESTful API integration. The RacoWireless Omega Management Suite & DevCloud processes are handled by the Omega Richochet API, enabling the ability for device mana […]
  • Stock Quote
    Markit on Demand's Stock Quote API is useful for finding the current value of a company’s stock. The response of this API contains price information for companies traded on the BATS Exchange in the United States. The result set includes BATS’ most current trading price of the share, the volume of that company’s stock, the change and change percent since […]
  • SimilarWeb Website Engagement
    The Engagement API could be beneficial for developers who want to obtain 3 web engagement results when they access a website. Because this API is about engagement, developers could create applications with improved functionality and accessibility. The results will display in either XML or JSON. The metrics provided are average page views, average time on sit […]
  • SimilarWeb Website Referrals
    SimilarWeb Referrals API could be useful for developers who want to obtain the 10 main websites that will redirect activity to the principal domain in XML or JSON formats. This API can be valuable if developers have wondered which domains are redirecting traffic to a website, especially because it could predict a successful web stream. To start app creation, […]
  • SimilarWeb Website Traffic
    To obtain a projected number of web visitors, developers can access SimilarWeb’s Traffic API which will display results in XML or JSON. This API is about traffic and it is valuable to monitor visitors' flow. From the amount of data to the number of visitors, this API could help developers to keep track of last month’s movement. With this API, developers […]
  • SimilarWeb Website Search Keywords
    SimilarWeb offers website and application analytics. The Search Keywords API could be useful for developers who want to obtain 3 keyword search results when they access a website. This API is about keyword search and it is valuable to measure search results for users who visit webpages from multiple mobile devices. To develop an app, developers can visit the […]