Dry Bulk Shipping Stocks: An experiment in self-clustering technology

-


Dry Bulk shipping companies are those that carry raw materials such as coal, iron ore, grain, fertilisers and chemicals in their specialized ships. The demand for dry bulk shipping is a good leading indicator of the health of the world economy. The Baltic Dry Index is an index of freight rates for dry bulk shipping as compiled by the Baltic Exchange in London. Since October, the BDI has gone down by 40 %, and with it the share price of the dry bulk shippers.
In this experiment, using the Self-Organising Maps [SOM] in http://www.viscovery.net software. [for more on Self-Organizing Maps see http://en.wikipedia.org/wiki/Self-organizing_map ] we took the data for 156 stocks from the Transportation Sector. The data included the output of ValuEngine's quantitative models and covered variables such as Valuation, EPS growth, 1 year-forecast retrun %, 1-month forecast return%, P/E ratio, Sharpe Ratio, 1 yr return %, 5 -yr return % etc. There were more than 30 variables. For more on ValuEngine, see http://www.valuengine.com/
Each stock was given a letter of the alphabet based on the transportation industry it was in viz: A=Airline, R=Railroad, T=Trucking, S=Shipping, M=MultiIndustry transportation. The dry bulk shippers thus belong to the shipping industry. The SOM was constructed and allowed to learn the characteristics of each stock, and the inter-relationships between each of the 30 variables of each stock, with every other stock. In terms of a matrix, this would be equivalent to calculating the mathematical distance for each cell with every other cell, in a 156 row x 30 column matrix. And distilling the essence of these inter-relationships to present it on a two-dimensional SOM.
The top image is a map showing 6 clusters [6 colors]. Although there is some semblance of clustering, such as that many stocks from R and T being in the Purple cluster in the North-East corner, in general, A, S, T, R and M can be found in any of the 6 clusters. What this means is that for stock picking, it matters less which industry the stock is in, and more on the qualities of each company.
However, one group of stocks forms a very distinctive cluster by itself. The Dry Bulk Shippers in Green cluster in the South West corner of the map. The SOM was not informed beforehand that these were the dry bulk shippers. The SOM placed them in a separate cluster based on their distinctive characteristics. There are no other Dry Bulk Shippers elsewhere on the map. We identified and re-labeled the dry bulk shippers with their ticker symbols instead of the former 'S' with which they were labeled when constructing the SOM. * in fact when we looked up the business descriptions of all the stocks in the dry bulk cluster, we found two other dry bulk shippers. We did not know about these companies, but the SOM correctly identified and placed them in the same cluster as the other dry bulk shippers.
In the bottom image, all the transport stocks are placed on a SOM that shows Composite Rank, in terms of Valuation and Momentum. The higher the score the more intense the color towards red. See scale at bottom of map. It is interesting that the dry bulk shippers have the highest score.
The dry bulk shippers are:
DRYS: Dryships Inc
EXM: Excel Maritime
EGLE: Eagle Bulk Shipping
DSX: Diana Shipping Co.
QMAR: Quintana Maritime
GNK: Genko Shipping
ESEA: Euroseas :Ltd
TBSI: TBS International
**** for more articles on the stock market, visit my other Blog at http://adrtracker.blogspot.com

Comments

Post a Comment

Popular posts from this blog

A Comparison of Four Noise Reduction Algorithms as Applied to the BSE Sensex index.

-
Image
Chart 1: Noise Reduction Algorithms Compared. Data as of 12 June 2025 As compared with established and mature stock exchanges such as the New York, Japanese and European stock exchanges, frontier and emerging stock exchanges have a higher level of ‘noise’. In financial markets, "noise" refers to the erratic and often unpredictable fluctuations in price and volume that can make it difficult to discern genuine market trends. This noise can stem from various sources, including news reports, market sentiment, and even algorithmic trading. It essentially obscures the underlying fundamental value of an asset, making it difficult for investors to make sound decision. In this post, I am applying four types of de-noising algorithms on the Bombay Stock Exchange Sensex Index (“BSE” or “Sensex”). My hypothesis is that the Sensex  has  a high level of noise. This is because a large proportion of the investors on the approximately 5000 stocks listed on the BSE are retail investors stee...
Read more

My Heart Belongs To The South

-
Image
Pictures from top: 1. The Confederate flag 2.Manatees: Malabar, Central Florida 3. My good friend Steve Thorpe with NASCAR racer. 4. Welcome to Georgia signboard 5. A Sunday aftertoon blue grass jam. 6. Carwash girl Melbourne, Florida 7. The Desert Inn at Yeehaw Junction near Kissimmee 8. Deep-fried duck with black-eyed peas and collard greens 9.Menu at the Marsh Landing restaurant, Fellmere, Florida 10. Barbecue joint in Mount Doro, Florida I moved to Princeton, New Jersey recently, after a year's stay in Melbourne, Florida. Melbourne is on the east coast of the Florida peninsula, right in the center between Jacksonville in the North and Miami in the south. Florida north of Fort Lauderdale is pretty much Southern USA. Not the caribbean culture of Miami and The Keys. Central Florida is more like Georgia and the Carolinas, though with some differences due to it's geographical features and climate. The land of alligators and swamps, cattle ranchers and cowboys called crackers, ci...
Read more