The Result
Created an API for ICD-10 codes prediction using ML models. The models are hosted on the Hugging Face platform. Created API that automates new data preparation and model retraining cycle.
The Result
Reduced cost of data storage and support due to the migrated corporate data warehouse infrastructure that simplified data management.
Increased performance of data querying and data availability for analytics due to execution of the most critical workloads on top of Snowflake’s multi-cluster shared data architecture.
The Result
A Python script for converting text data from PDF files to txt files. All text documents were split into paragraphs using regular expressions. Newly created text files were saved into the Google Drive folder for further processing.
The Result
Brought into action, tested and verified accounting system with individual log-ins for employees and managers that calculates their customized salaries, based on the exact amount of working days, reduced business days, vacations, days off, etc.
The Result
The Mellivora’s NLP team has developed a configurable NLP solution for concept and named entity recognition from texts of different European languages which can be applied for multiple use cases aimed at semantic search, business domain knowledge modelling and analytics, virtual assistant, opinion mining, sentiment analysis.
The Result
A crafted workflow to support MRR (Monthly Recurring Revenue) reports. Further ongoing support, maintenance and modifying Oozie workflows and reports according to the changing industry’s and business requirements.
The Result
Created a database for online clinic chatbot to support automatic filling anamnesis from the clients. The bot is recognizing the client’s answer and filled the json document (it is very simple by using AWS service). If the quality of the json document is not sufficient (not enough data - TensorFlow) some additional questions are generated and result json documents are merged.
The Result
A completed prototype for eHealth consumer app that provides preliminary skin problems diagnosis and recommendations based on image recognition analysis of the problematic skin area.
The Result
A brought into circulation system of traffic management and road traffic control. Under supervision of Mellivora experts, software and analytical platform were successfully developed and implemented throughout several regions.
The Result
Delivered software that allowed the client to trace the cases of the drugs’ positive or negative (side) effects, thus helping them to provide healthcare insights, based on sentiment analysis and statistics methods. The client is now equipped with the software to predict financial markets’ indices of the pharmaceutics.