Google uses Natural Language Processing (NLP) routines to convert its understanding of text into topics and concepts (Entities). We looked out how much understanding Google misses using this approach in the Finance sector.
InLinks analyzed the page content of the top 10 Google results (in the Singapore Market) ranking for the phrase Gold Price and compared the Named Entities recognized by Google’s NLP API with the proprietory routines designed by Inlinks to uncover gaps in Google’s machine learning in the Finance sector
The results showed that 20.2% of entities seen on the results in the Finance sector SERPS (search engine Results pages) were positively identified by Google.
This compares to 21.4% average across all analyzed industry sectors.
Different sectors tend to be analyzed with a different degree of accuracy by the search engines. This stems from two main challenges.
|Finance Industry||Google Analysis||InLinks Analysis|
|Avg. Number of words per page||1506|
|Avg. Number of Topics per page||9.8||48.3|
|Benchmark - Avg. nb of entities/page (all sectors)||9.6||46.1|
|Of which, Topic types are:|
|- Cities & geo. areas||19||24|
Google’s Search API returned URLs for the following sites competing for this phrase:
#sbma.org.sg, #bullionstar, #cmcmarkets, #ig, #meysonjewellery, #mustafa.com.sg, #straitstimes
The texts of each page are then sent to Google’s NLP API, in order to determine which entities are identified by the search engine. These are important for search since Google is then able to link these to its Knowledge Graph to feed its services including Google Discover, Google search, Voice Search and Google News. (Although, correct identification does not guarantee inclusion in these results)
Here is first of all the synthesis of the results returned by Google:
Here are some errors in the categorization of entities:
By understanding where Google is failing to recognize important concepts within the industry, there is an opportunity for companies in the sector to write clearer content that Google can better understand.
Another option is to explicitly state these concepts in Webpage schema for machine learning algorithms to take into account. This would require using Schema.org/WebPage and the "about" and mentions" properties for important concepts such as Bank, Stock market, Futures exchange, Central bank.
Internal linking of topics topages dedicated to each important topic will also help to reduce cannibalisation of content in Google’s understanding of contect within your content.
Google's understanding of the Finance market, based on its NLP algorithms remains limited at 20.2% for this industry. Businesses either need to improve their schema or make their content more understandable by Google to improve its level of understanding.
Gold as an investment, Spot contract, London, Futures contract, Over-the-counter (finance), London bullion market, United States
IG Group, Singapore, United States, Discover Financial, Wall Street, Monetary Authority of Singapore, Belgium, Contract for difference
Singapore, The Straits Times, AsiaOne, WeChat, Obituary, Tamil Murasu, Jurong West, United States, China
Singapore, AsiaOne, The Straits Times, Exchange-traded fund, North America, Europe, WeChat, Tamil Murasu, Obituary, Enterprise Singapore, Singapore Exchange, Bloomberg L.P., London bullion market, Sydney, Asia, Goldman Sachs, United States, SPDR Gold Shares, India, China
United States, Barrick Gold, CMC Markets, John Maynard Keynes, Share (finance), Franco-Nevada, Newmont Corporation
Gold, Singapore, United States, Chicago Board Options Exchange, Exchange-traded fund, Over-the-counter (finance)
Japan, Malaysia, DBS Bank, POSB Bank, Mustafa Centre, India, Bahraini dinar, Danish krone, Pakistani rupee, Jordanian dinar, Norwegian krone, South African rand, Bangladeshi taka, Bangladesh
Gold as an investment, Gold, London bullion market, Singapore, Sunil Kashyap, Precious metal, Asia, Japan, South Africa, Taiwan, Malaysia, Russian language, London, Canada, Australia, Swiss franc, United Kingdom