Unlock endless possibilites with Moonshot's algorithms
See why Moonshot's algorithms which power our predictions are trusted by over 20 organisations! Here are example case studies of our algorithms for skin cancer prediction, DNA sequencing, mRNA vaccine development, environmental conservation, space research and more.
What do doctors do when a patient has trouble breathing? They use a ventilator to pump oxygen.
But mechanical ventilation is a clinician-intensive procedure, a limitation that was prominently on display during the COVID-19 pandemic.
Our fast algorithms were used by Dr. Carl McBride Ellis to visualize the huge ventilation dataset.
"Buy low, sell high." It sounds so easy. In reality, trading for profit has always been a difficult problem to solve. Electronic trading allows for thousands of transactions to occur in less than a second, resulting in nearly unlimited opportunities.
Dr. Carl McBride Ellis uses TSNE to visualize Jane Street’s huge dataset to predict stock market signals.
Predicting Stock Markets
“Are we alone in the Universe?” It’s one of the most profound human questions. As technology improves, we’re finding new and more powerful ways to seek answers.
Tawara from Japan used our fast algorithms to identify anomalous signals in scans of Breakthrough Listen targets. Because there are no confirmed examples of alien signals, SETI included some simulated signals.
Extraterrestrial Life Search
We must automate the identification of marine life to help overcome increasing human impacts on oceans, providing a critical tool for conservation science.
Currently, most research institutions rely on time intensive manual matching by the human eye. Awsaf uses TSNE to visualize whale and dolphin species by up to 100x faster than current implementations.
With the inevitable advancement of cancer research, AI can now automatically detect cancer through just analyzing images. However, speed was and still is a major issue.
The problem of speed was solved by using Moonshot's algos as Chris won the top $30,000 prize in the world to detect melanoma. He said “If you do this with Scikit Learn, it’ll literally take days. Now with t-SNE, it takes seconds!”
Detecting Cancer with AI
Improving Education Outcomes
Writing is a critical skill for success. However, less than a third of high school seniors are proficient writers. Low-income students fare even worse, with less than 15% demonstrating writing proficiency.
Darien and Chris used TSNE to help students improve writing via automated feedback tools.
Winning the fight against the COVID-19 pandemic will require an effective vaccine that can be equitably and widely distributed.
Currently, vaccines require many storage requirements and so Vatsal was able to integrate our algos to model and design rules for RNA degradation. The model predicts degradation rates at each base of an RNA molecule.
mRNA Vaccine modelling
Detecting Live Disaster Tweets
Twitter has become an important communication channel, allowing people to announce an emergency in real-time. But, it’s not always clear whether a person’s words are actually announcing a disaster.
xhulu built a machine learning model that predicts which Tweets are about real disasters and which one’s aren’t. Using t-SNE, they were able to project tweets from high-dimension to low-dimension (2d and 3d).
Ioannis helped CERN on using AI to detect the Higgs Boson particle. This kernel is about to try accelerated dimensionality education/clustering methods (t-SNE + UMAP) using the open-source RAPIDS GPU-library.
He applied these algos to the tabular data of Higgs-Boson problem for learning and discerning patterns.
Higgs Boson Particle
Without using our algos, Hiram said that his “computer just can’t handle all the data” and so the sequence just wouldn't run.
Now by integrating our algo, the entire DNA sequence can actually run and just takes 739 seconds to run!