The Data Analytics service can cover any phase of a data value extraction process: data acquisition and integration, data anonymization, data exploration and transformation, semantic metadata generation, machine learning, deep learning, data visualization, computer vision, natural language processing (NLP), data workflows implementation and management
This service aims to facilitate the application of Data Analytics methods and best practices and their uptake by the companies.
The Data Analytics service is requested whenever a data application (or part of it) has to be developed, whereas the Cineca Technical consulting is mostly involved when an application (or part of it) has already been developed and needs to be adapted to run on HPC resources to improve performances or scale up.
Depending on the requirements of the customer, the Data Analytics service may be limited to the design and implementation of a specific phase in the data analytics process (e.g. Machine Learning), up to the design and implementation of the whole process of data value extraction (business understanding, data acquisition and exploration, quality assessment, data transformation, visualization and analysis, model building, model evaluation, deployment).
The Data Analytics service is cross-domain and over heterogeneous data sources, comprising textual, audio and video data.
The service model is focused on the collaboration on projects with specific objectives, work plans and resources. It may include also consultations and training.
In particular, implementations in the pre-processing phase may include anonymisation techniques, outlier detection, missing data estimation, features extraction, dimensionality reduction, structuring and data cleaning.
Implementations in the data analytics phase include application of clustering techniques (partitioning methods, hierarchical clustering, fuzzy clustering, density-based clustering, model-based clustering), association rules, sequential patterns, graph analysis, predictive modelling (decision trees, random forests, neural networks, DNN, KNN, SVM, naive Bayes, regression, regression trees, symbolic regression), econometric models, building of indicators and dashboards, text mining, semantic annotation, keyframe extraction, speech recognition, image classification.
The service also provides data visualization, interactive virtual environment creation, rendering, digital twins.
Users that need to extract value from data in any domain and need to be supported with data analytics competences
1. Predictive maintenance for an automotive components manufacture based on data collected by onboard devices
2. Virtual environments connected to real time production data (digital twin)
3. Forecasting models for time series in manufacturing processes
4. Precision agriculture: weather forecasting at high resolution (data generation) and integration with field data, machine learning models generation and testing, results visualization
5. Recommendation system for a game company
6. Sentiment analysis for Reggia di Caserta (Caserta Royal Palace)