Creating an identification system using Bitcoin’s Base58Check encoding

Non-Sequential Base Systems Bitcoin’s Base58 Base58 is a binary to text encoding developed for displaying the 20-byte integer representing a Bitcoin address. Base58 is the same as base 64, but without the +, /, 0, O, I, and l symbols. 123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz The encoding prevents confusion between letters, especially when handwritten and across different fonts. The…

Read More


Text generation in Python

Text is my personal favorite medium for machine learning. Here is why: In computing, a picture is worth a (few hundred) thousand words. As a result, modeling text is more space and compute efficient than visual models. Text arrived first to the internet. This lead time has resulted in better algorithms, and bottomless data. Interpretability…

Read More


Real-time event discovery using Wikipedia edits

This article has been updated to reflect changes suggested by one of our readers. Thanks Andrew! New information, released in an instant, can synchronize the behavior of millions of people. This is magnified by the impact of the information, and the transience of its release. Wikipedia editors edit related pages during such events, reducing the…

Read More


Writing better job postings using Glassdoor data

Since the launch of its public beta in 2008, Glassdoor has become the gold standard for company satisfaction ratings. They also have a classifieds section comparable to LinkedIn, Indeed, and others. Glassdoor provides examples of job descriptions with company ratings in context. This makes it easy to compare what good and bad companies have in…

Read More



Bridging concepts by applying pathfinding to word vectors

Society has unlocked vast amounts of value by harnessing the power of the graphs. First, we used graphs as infrastructure for running water, electricity, and the internet. Then, we used graphs as platforms for further applications. The refrigerator and washing machine are second-layer graph technologies, as are Google and Facebook. The networks people are looking…

Read More



Building a recommendation system using product embeddings

For competitive, low-margin businesses, a store’s layout can be the difference between surviving and getting wiped out. To drive more sales, businesses are using recommendation systems in online stores, and data-driven nudging at brick-and-mortar locations. How can purchasing data be turned into sales? We can use an unaltered version of the word2vec algorithm used in…

Read More