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.

  • Diffbot Image
    Diffbot provides developers tools that can identify, analyze, and extract the main content and sections from any web page. The purpose of Diffbot’s Image API is to extract the main images from web pages. The Image API can analyze a web page and return full details on the extracted images. Date Updated: 2014-10-20 Tags: [field_primary_category], [field_second […]
  • Diffbot Analyze
    Diffbot provides developers tools that can identify, analyze, and extract the main content and sections from any web page. The Diffbot Analyze API can analyze a web page visually, and take a URL and identify what type of page it is. Diffbot’s Analyze API can then decide which Diffbot extraction API (article, discussion, image, or product) may be appropriate, […]
  • Diffbot Discussion
    Diffbot provides developers tools that can identify, analyze, and extract the main content and sections from any web page. The Diffbot Discussion API extracts discussions and posting information from web pages. It can return information about all identified objects on a submitted page and the Discussion API returns all post data in a single object. The Diffb […]
  • Crowdfunder
    Crowdfunder is a UK based platform where people can crowdsource funding for unique projects. Crowdfunder projects typically involve social endeavors related to community, charity, environment, art, music, publishing, film, and theatre. Currently in an open beta, HTTP GET calls to the Crowdfunder API can be made to request JSON lists of all current campaigns […]
  • GlobalNLP
    Via RESTful connectivity, GlobalNLP handles a wide variety of natural language processing. Currently, the API supports many NLP processes including: stemming, morphological synthesis, word sense disambiguation, entity extraction, and automatic translation. A full list of supported processes is listed in the documentation along with code samples in JavaScript […]
  • bx.in.th
    bx.in.th is a Thailand-based Bitcoin and cryptocurrency exchange platform operated by Bitcoin Exchange Thailand (Bitcoin Co. Ltd.). Their API accessibility is divided into Public and Private. The bx.in.th Public API allows anyone to view market data from the exchange, including rates, orderbook, currency pairing for comparison, high and low trades, average B […]
  • Company Check
    The Company Check API provides direct access to a wealth of information on companies and directors. The API platform is useful to developers to incorporate company, director, financial, credit data, and many more data fields into software and business apps. By applying for the API Key, developers can choose between different levels of account plans. Date Upd […]
  • VIDAL Group
    VIDAL Group is a French healthcare informatics group specializing in databasing and distributing healthcare data, pharmaceutical information, treatment specifications, and scientific publications for patients and healthcare practitioners in the European continent and worldwide. VIDAL Group also supports a medical software application under the same name. VID […]
  • Coinzone
    Based in Amsterdam, Coinzone enables European online retailers and eCommerce providers to accept digital currencies such as Bitcoin instead of traditional payment methods. Using the Coinzone REST API, secure calls can be made to authenticate, initiate transactions, retrieve transaction details, and process refunds. Authentication requires a client-code, time […]
  • LakeBTC
    LakeBTC is a Chinese based BitCoin exchange service. Using their REST API, developers can make requests to the Market Data ticker to receive information on the last price, best bid, best ask, 24-hour high and 24-hour low prices in New York and the United States. Calls to the API may also be made to return information from the 'Orderbook,' and […]