StoryFit uses Import.io data and AI to spot a hit manuscript

For StoryFit, data is the fuel that powers its predictive analytic engines. StoryFit's artificial intelligence and machine learning algorithms are trained using vast amounts of data culled from a variety of sources, including Import.io extractors. This data contributes to StoryFit's core NLP-focused AI. "Our machine learning models compare tens of thousands of elements within books and movies to identify audience fit and make market recommendations for books, movies and television programming," said Monica Landers, CEO.

"Our product starts with gathering the right data," said Mark Bessen, director of product. "There's so much valuable data on the web about what movies and books people are talking about, how much traction content is gaining, and who is consuming that content. But harnessing that data is a challenge."

Scalable, Automated Data Extraction

StoryFit quickly realized that gathering online data in real time was essential. Import.io offered a scalable, automated way to gather vast amounts of data across hundreds of thousands of web pages. Using Import.io, StoryFit mined web sites to gather all available data related to books, movies and television. For example, movie data included descriptions, actors and production companies as well as ratings and reviews.

"We used Import.io to help build out our dataset, which includes data extracted from more than 200,000 web sites. This database has information about every movie and book we can get our hands on," said Bessen.

"Using Import.io, we can focus on finding the right data sources without needing to reinvent the wheel on how to gather it," said Bessen. "And, with Import.io, we can just download the data in a tabular format and it's ready to go – no tedious parsing of web formatted data."

Ongoing Data Acquisition

StoryFit continues to update its core dataset, using Import.io to gather new data about existing works and content for new books, movies and shows. "Import.io has significantly sped up the data extractions that keep our dataset updated with the latest information, like new reviews. With Import.io, we are able to batch run all 200,000 queries in a single go and can get results with a 24 hour window. This would have taken at least two weeks before," said Bessen.

Data is also collected to track how users are interacting with related content online. "For books, we stay on top of trends by gathering and analyzing metadata, customer views and other behavioral data related to top-performing content. This gives us a deep insight into books on best-seller lists and ensures that we have a comprehensive view into the publishing market," said Landers. "This is powered by Import.io-sourced data and it definitely gives us a competitive advantage."

StoryFit also tracks performance of content for its clients. "Import.io extractors are run against 10,000 titles and growing every day so we can see how rank and sale performance is doing. Periodically, we run additional titles to get a broader view into all books or movies in a market over a certain date range," said Bessen. "We also use Import.io to gather data that allows us to track the performance of the top books and movies. This allows us to identify trends."

Maintaining Competitive Edge

"Within the entertainment and publishing industries, we see new entrants in the AI space, but our underlying technology of Natural Language Processing on the content, coupled with rich data that we are able to gather using Import.io, gives us another notch up on the competition," said Landers.

Customer understanding of the power of StoryFit's solutions is also keeping it ahead of its competitors. "We enable our customers to make business decisions based on data-driven insights using data sourced with Import.io. They are able to assess the viability and sales potential of projects based on data and sophisticated analytics, letting the companies move smarter and more efficiently," said Landers.

"Import.io has also accelerated our product roadmap. Because we are able to depend on Import.io for bulk data extraction, we are able to go faster and keep our focus on product development. We look forward to continuing our rewarding partnership with Import.io," Bessen concluded.

Visit www.import.io to find out more.

SOURCE Import.io

Related Links

http://www.import.io