Problem

Nowadays there is an urgent need for forecasting automatisms with near real-time frequency.
It is required In any industrial context, not only finance, but e.g. IOT for making prevention.

Humanativa – Tools and Expertise

Auto-Forecast Module in the TimeSeries context

• For the EDA (Exploratory Data Analysis) phase, introduces deep data analysis techniques over time
• for the Model Production phase, introduces an Auto-Forecast engine that exploits the results of the analysis of the EDA phase to automatically define a protocol for the production of an efficient model.
• For the MLOps phase: to automatically replicate Model and Pipeline in various MLOps environments in the Cloud to prepare for Production.

Benefits

• Decreased EDA time
• Decrease in Learning Time
• Decrease in re-training time (MLOps)

Use Case

• Industry: Banking
  Use case: Customer insight per Up e Cross selling – Forecast
• Industry: Automotive – Smartcity
  Use case: Vehicle Flow forecast & Behavioural profiling
• Industry: AIR Transportation – IOT
  Use case: Passenger Flow Forecast

Problem

Information deducible from Images, Video, Audio is increasingly available digitally. Their analysis can support humans in contexts such as medicine, robotics, control systems, security, etc.

The market demand is for more and more precise and efficient AI tools for real-time analysis to accompany e.g. medical image analysis, artificial vision for industrial robotics, quality control in production, automotive traffic safety, etc..

Humanativa – Tools and Expertise

CNN Framework (Convolutional Neural Network)

Convolutional Neural Networks are constantly evolving. Humanativa has a framework that uses the most effective and fastest CNN libraries, offering:

• an Object Detection/Classification model
• a pipeline in which, in addition to the first stage of Object Detection in inference mode, it is possible to insert other stages that enrich the Object Detection analysis depending on the context in which they have to be applied.
• For example, in the automotive context of risk event control, Humanativa has developed a Tracking library for counting vehicles in the lanes of Routine Driving, Overtaking and Fast Overtaking in a motorway context.

Benefits

• Improve safety supervision capabilities
  E.g. in the automotive traffic field
• Provide diagnostic support
  E.g. in the medical field

Use Case

• Industry: Automotive
  Use case: Highway Control
  Automatic Incident Detection (AID), such as the detection of stopped vehicles, wrong-way vehicles, pedestrians and traffic congestion.

Problem

Answering the frequent Client question:

“Know the behaviour to prevent deviations from the standard behaviour of its Products/Services/Customers”.

Humanativa – Tools and Expertise

Clustering

Clustering is a technique of subdividing a population or ‘data points’ by grouping them into different clusters on the basis of similarity and dissimilarity between them.

Clustering processes are widely known to the specialist community, and a fair variety of algorithms exist in the literature, but in Humanativa we apply a two-level clustering criterion, refining clusters for ‘robust’ and self-consistent behavioural patterns.

We fill a gap in the market by offering a rigorous protocol that, starting from literature algorithms, performs a grid-search, analogous to the one most widely used in the field of supervised problems, in order to compete several algorithms in several parameter configurations and identify which is the most ‘efficient’ among the competing models.

Benefits

• Understanding Customer/Product Segmentations and how the ‘population’ of segments moves over time through multiple observations of patterns.
• Very useful in the Data Preparation (ML) phase to understand the Value of Data right from the Analysis phase.

Use Case

• Industry: Banking
  Use case: Securitisation Analysis (NPL) – Customer insight for Up – Cross selling – Leasing Analytics – Credit Risk
• Industry: Automotive – Smartcity
  Use case: Behavioural profiling in Vehicle Flow – Behavioural analytics & accident risks
• Industry: Energy
  Use Case: Credit Collection

Problem

Text, whether digitised or from paper sources, contains information that is often not retrievable in advanced analytics.
There are many contexts in which the information to be retrieved is also crucial for building ML-based analyses.
Just think of diagnoses in the medical field, or court documents in the legal field, or even documents of government, institutions, security, etc…

Humanativa – Tools and Expertise

Language Processing (NLP) & Text Mining

In AI and Machine Learning processes, text is one of the sources on which Data Preparation needs additional techniques to add information to the data.

Information ‘derived’ with Text Mining or Sentiment Analysis or other natural language related techniques are the solution where the information domain needs to be reinforced before applying ML algorithms.

The recent partnership (2023) signed with Expert.ai adds more robustness to Humanativa’s AI and ML solutions.

Expert.ai is a leading company in natural language software services. Many organisations in the insurance, banking and finance, publishing, media and defence industries rely on expert.ai to transform language into data, analyse and understand complex documents, and accelerate process automation.

Benefits

Text analysis with the Expert.ai platform helps to build ‘enriched datasets’ for any supervised or unsupervised ML service request, because it enriches the information with additional analytics regarding the source textual data.

Use Case

There are strategies in place and use cases in progress to integrate Humanativa experiences with Expert.ai experiences in order to strengthen our joint service offering.