Owners
Spatial Geo-Data Visualization and Aggregation Engine
In collaboration with Owners, we are building next-generation tools for analysts and service providers to easily understand geo-based market dynamics.
This involves the understanding and definition of key indicators for end users, developing a geo-spatial engine for data navigation and deploying it internally for Owners' partners use.
Evernia Bio
Soil microbial characterization
Microbiological research for understanding the implications of quantifying soil microorganisms in Regenerative Agriculture.
Development of Deep Learning based microscopy solution to identify, count and estimate biomass of soil microorganisms.
Ideation and definition of technical and business roadmaps for the deployment of the designed solution.
7 Chord
Data strategy for bond predictive pricing & trend forecasting apps
Built and evaluated machine learning approach to determine the fair price of a corporate bond. Conducted analysis to decompose the fair value into curve and structural liquidity components.
Evaluated different data sources from vendors to determine the data to be used in production.
Sight Walk
Alternative routing app for city strolling
Web mapping services such as Gmaps only suggest the shortest route (in terms of distance and/or time). The goal of this project was to automatically suggest alternative more enjoyable routes, which might take marginally more time but go through spots that would be more interesting to the user.
In order to do that, we defined a scoring function that weights each path based on social media data. Afterwards, we proposed two new graph based optimization algorithms and developed a POC.
Liveperson
HR Analytics. Performance - Hiring
This was a special project for the CEO that consisted in restructuring the whole HR area based on HR Analytics.
Computed Employee performance metrics, hiring performance metrics and area efficiency metrics to propose a new HR org. Worked closely to Edgar Papke on aligning the company's culture.
Spliff
Set list planner for DJs
Spliff is a venture created to develop new algorithms for music libraries exploration and organization.
The goal is to allow DJs to plan DJ sets in a smarter way than current tools available in the market. By choosing a set of rules such as harmonic mixing, set length and BPM constraints, Spliff’s AI is able to assist DJs' in planning their sets by suggesting customized alternatives at every time step.
Ultimately DJs should be able to plan and visualize several metrics of the set in a much faster and intelligent way.