Applying Natural Language Processing to Automate Pharmacy Processes

AGM, a globally operating digital marketing agency, develops advertising strategies and executes online marketing campaigns for its customers from a broad range of sectors. Their challenge was to determine the best possible allocation of marketing funds among multiple online channels, optimizing the overall effectiveness and return of investment of its marketing campaigns.

Each of the online channels, from search engines to video-sharing and social platforms, provided analytics data in different formats and at different time intervals. In order to implement a data-driven solution that spans all channels, Wolfram Consulting Group’s first task was to build a fully automated data acquisition pipeline and normalize the available information into a representation suitable for computation.

Then, using a multivariate time-series forecasting algorithm tailored for the kind of data AGM provided from their previous campaigns, we developed and tested a tool that could accurately and reliably predict the evolution of the outcomes of the different channels. During the course of an ongoing campaign, this tool was used to propose reallocation of spending over different channels so AGM could dynamically optimize the overall return on investment.

Finally, we extended the algorithm so AGM could either calculate the budget necessary to achieve a chosen outcome KPI or, alternatively, forecast the outcome for a given budget.

Wolfram experts provided AGM with an easy-to-use graphical user interface to explore “what-if” questions and visualize a wide range of scenarios. Our solution for AGM attracted new clients who were seeking cutting-edge approaches to managing their digital campaigns.

Offshore wind is one of the most important sources of renewable energy and a key area of interest for one of Wolfram Consulting Group’s clients. To get a complete understanding of the multitude of factors that contribute to the technical and financial performance of a wind farm, our client’s challenge was to design and develop a complete software package for modeling offshore wind operations.

The model needed to connect a large variety of different data types and determine their effects on each other. Meteorological conditions, equipment reliability characteristics and investment in maintenance resources all interact and can have a significant impact on the profitability of a project, making this a complex modeling challenge.

What they needed was a high-performance computation environment that could provide industrial-grade reliability at scale. Wolfram Consulting implemented an effective software solution that processes meteorological and oceanic datasets, provides robust statistical and analytical capabilities, and adds advanced visualizations.

The client then used Wolfram’s technology to analyze the datasets, deriving statistics and fitting distributions and parametric models to compute persistence metrics—the probability that a given event lasts for a certain amount of time. In addition, time series analytics were used to quickly convert disparate datasets and make them usable by the discrete-event simulation system.

This solution has been deployed in the field to assist and support multibillion-euro development projects in European offshore wind by global energy and utilities organizations.

From the beginning, the founders of the biotechnology startup Emerald Therapeutics wanted to develop an ideal research platform that would allow for lab and process automation during experiments as well as easy communication of their findings.

Mathematica provides all the tools the Emerald founders needed to carry out their vision, while Wolfram Language powers Emerald Cloud Laboratory, a web-based life science lab.

Regarding the decision to use Mathematica, Emerald cofounder and co-CEO Brian Frezza says, “It struck the perfect balance of being powerful enough and versatile enough to allow our engineering team to develop sophisticated software within, yet the language is easy enough to learn that it’s accessible to our chemists and biologists to use as a primary means of keeping a daily lab notebook.”

Emerald’s team of scientists and engineers have a shared code base in Mathematica, which allows them to use one platform to carry out all the tasks in their antiviral research workflow—from developing functions to processing and storing data, designing and managing experiments, presenting findings, even controlling lab instruments.

Having Mathematica as the core platform means the Emerald team can trust the repeatability and accuracy of its results and rapidly grow its experiment base. “We can keep handling larger experiments and we can do more complicated things each day because we’re building on a base that is incredibly reliable and precise… You need that level of reproducibility in biology. You need something that can handle all the quantitative detail in a way that’s still accessible and manipulatable to the scientists.”

For Frezza, having one language that both the engineers and scientists can share and perfect is extremely valuable, especially for a startup in the pharmaceutical industry. “The way in which we’re able to build is just incredible. Our burn rate is incredibly low for a startup because the number of people we need to do what we’re doing, which is incredibly ambitious, it scales incredibly well when you have a tool like that.”