Mosaic provides efficient and effective algorithm and model deployment services. In collaboration with our customers, we prototype a number of different candidate machine learning models, and eventually select the top performers to be deployed enterprise-wide.
Deployment into your existing IT infrastructure requires a different skill set than algorithm design and selection. Our data scientists are well versed in a number of data platforms and are adept at integrating R and/or Python scripts into consumable reports, dashboards or visualizations.
Anytime you wish to predict the transient state(s) of something or someone constantly monitored by sensors, time series classifications are the right tool. This article will explain some basic concepts of using deep learning models for TSC and finish with a brief discussion of ways to improve the performance to save on cost and speed.
Algorithms can be trained to mimic human behavior, but what happens when the human developing the algorithm inadvertently allows bias into the training process?
Mosaic writes an in-depth view on the synergies between design thinking & data science. We also examine how these two disciplines can be used together.
We designed and deployed a custom deep learning based tool to extract images from millions of digital and scanned documents.
In our white paper, Mosaic examines fresh machine learning based approaches to more accurately forecast airline seat demand.
Mosaic helps a leading 3PL company apply machine learning to predict brokerage profit drivers.
This whitepaper reviews an approach for applying machine learning and predictive analytics in a B2B sales & marketing environment.
Mosaic was engaged by a leading hotel chain to assess the best way to predict future demand for hotel rooms across their various properties.
We designed and deployed an AI model to predict shipments at risk of late fees for one of the world’s largest CPG businesses.
For one of the US’s largest healthcare systems, Mosaic designed and deployed a custom machine learning tool to identify anomalous purchase orders.