Cairstair
December 27, 2016
I have created a widget based on a prediction algorithm. This algorithm establishes word order based on a large quanitity of data.
This algorithm will provide improved typing speed while providing the three most likely words that will follow.
The Prediction Algorithm wideget allows a custom word/phrase to be entered. Then based on the input it will predict the next word and provide three plausable options.
My Prediction Algorithm uses the HC Corpora data set to determin word frequency.
The HC Corpora data set is cleaned to remove extra letters/characters and then is categorized into the most frequent word combinations (N-grams).
Using these N-gram frequencies My Prediction Algorithm can take submitted sentences/words and calculate the most likely next word.
I greatly appreciate you taking your time to review my Data Science Capstone Project/Presentation.
Any advice and/or comments is greatly appreciated.