Trustworthy AI

When using AI models in environments where compliance standards are important, Mosaic Factor can help your company be on top of data governance by applying trustworthy AI solutions.

View solution

Synthetic Data

Synthetic data is artificial data generated from original data using a model trained to reproduce its characteristics and structure.

View solution

Descriptive Models

Descriptive models aim to describe patterns, relationships, and structures within data. They don’t predict future outcomes but provide insights into existing phenomena.

View solution

Predictive Models

Predictive modelling, also known as predictive analytics, is a discipline that uses statistical, mathematical and artificial intelligence techniques to predict future outcomes based on historical data.

View solution

LLMs

At Mosaic Factor, we focus on the creation of domain specific LLMs (or light Large Language Models) for our client organisations.

View solution

Digital Twins

To allow your business to monitor and optimise your assets in real-time Mosaic Factor uses Digital Twins. They can predict failures, detect inefficiencies, and improve decision-making through the use of data.

View solution

Data Enhanced Products

Through different data sources (ie. physical tests) and ML models and usually in combination with our digital twin solutions, our data enhancement solution can learn, predict, and simulate outcomes to provide automatic product configurations that result in product and component improvement during the development process.

View solution

Data As a Service Products

Data as a Service (DaaS) is a cloud-based model that allows companies to access, manage, and analyse data on demand, without the need for extensive on-premise infrastructure.

View solution

Predictive Maintenance

For Predictive maintenance models, we use historical and real-time data to anticipate equipment failures or maintenance needs. By analysing sensor data, maintenance logs, and other relevant information, we can schedule maintenance proactively, reduce downtime, and extend the lifespan of your machinery.

View solution

Demand Cost Forecasting

Our predictive models help businesses forecast demand for products or services. By analysing historical sales data, seasonality, economic factors, and external events we can optimise inventory levels, allocate resources efficiently, and minimise overstock or stockouts.

View solution

Quality Analytics

We identify patterns that correlate with defects or quality issues, allowing your business to take corrective actions early and maintain high-quality standards.

View solution

Inventory Management

We use predictive models to optimise inventory levels by considering factors such as lead time, demand variability, and storage costs.

View solution

Supply Chain Management

We can use historical and real-time data analytics to manage the supply chain, optimise transportation and ensure on-time product delivery.

View solution

Market Understanding

Our descriptive AI models provide valuable insights for decision-making and understanding complex systems of your organisation.

View solution

Pattern Exploration

Our descriptive AI models provide valuable insights for decision-making and understanding complex systems of your organisation.

View solution

Logistics

Logistics

Mosaic Factor’s higher priority in Logistics is sharing key data across different Supply Chain players to optimise performance while managing sustainability by mitigating the impact of these operations.

View industry

Automotive

B:SM Tram Parquímetre

Mosaic Factor’s apply AI solutions in various aspects of the automotive industry, usually by enhancing vehicles and its components during its development.

View industry

Mobility

Mobility

Mosaic Factor’s higher priority in Mobility is to optimise transport systems to people’s mobility while improving overall security and sustainability of transport solutions.

View industry

Corporate Services

Corporate Services

Our machine learning and complex algorithms help organisations manage compliance and customer service to increase the service level of your organization while optimising resolution time for several processes.

View industry

Manufacturing

Manufacturing

Mosaic Factor’s higher priority in Manufacturing is aid our clients decrease costs, increase sustainability while streamlining the production chain.

View industry

Healthcare

Healthcare

Mosaic Factor’s higher priority in Healthcare is making use of data to improve patient care and monitoring in a safe manner to optimise healthcare systems resources and assisting healthcare professionals.

View industry

Projects

Disruptive

Detection and classification of disruptions’ model.

Client

Funded by the Spanish Government

Partners

The problem

Logistics networks are highly vulnerable to disruptions whose size and number are gradually increasing both locally and globally.

Despite recent efforts to improve the understanding of logistics networks and their potential setbacks, as well as technological advancements and digitisation in the field, there remains a need for a new approach or method to monitor logistics networks capable of performing a more complete and comprehensive analysis.

Our solution had to take into account the different types of factors that can disrupt logistics, including:

    • Factors related to operations
    • Weather patterns
    • Natural phenomena or extreme conditions
    • Political instability
    • Markets instability and others.

The solution had to be scalable enough to cover entire logistics networks and incorporate all the main components of these networks

The solution

The solution of the project is a system capable to collect news, detect and classify disruption of the logistics networks, include all this information in a data lake and, finally, visualise both the news and the disruptions identified using different filters depending on customer’s needs.

The overall system architecture is shown in the figure below:

The system is composed of several interconnected components that work together to collect, process, and analyse data (news) as follows:

Data Sources: This is the foundation for generating disruptions.

    • Bing News Search: Main news source during the initial phase.
    • Scraping: Considered for the second phase, which will allow obtaining news from other relevant portals and delve deeper into them.

Disruptive system: The main system responsible for identifying, generating, and classifying disruptions based on news from data sources.

    • Data collection: News is collected using the Bing News Search API on a daily basis, as explained in the previous section.
    • Disruption Detection: The artificial intelligence model, ChatGPT, analyses the news to detect and catalog disruptions. This integration is also done through an API.
    • Data Fusion: Integration of new disruptions with previously recorded ones to improve system cohesion and reliability, helping the end user to have a greater vision and understanding of the system.
    • Entity Identification: Identification of locations, infrastructures, and relevant stakeholders that can help detect which disruptions are related to nodes or operators of interest to the end customer.

Artificial Intelligence model:

    • Chat GPT: Responsible for detecting disruptions, classifying them according to their type and associated topics, and associating them with previous disruptions.

Data Lake:

    • Database: Central repository for storing data before and after processing. This means storing both news and generated disruptions.

Frontend:

    • Retriever: Graphical interface that connects to the database through an API and is responsible for displaying disruptions and their related news and entities. It also allows sorting and filtering news by type, first and last detection dates, and status, as well as by the various entities to which the disruption is associated.

Data

The data lake has been designed as a repository to collect potentially relevant digital news from any source, in order to process and analyse them for disruptions. During this initial phase, Bing News Search was used as the data source. The following are the different attributes that exist in the data lake, distinguishing between raw data, i.e., initial data obtained through Bing News search, and data processed by the disruption detection and classification model.

Results

Phase 2 of this project is going to be presented to the Spanish government. Here it is how the interface looks like at the moment:

The disruptive system can be visualised live through this link: http://disruptive-retriever-fe-prod.apps.mosaicfactor.es

Do you have any questions?

We are always ready to help you and answer your questions. 





    *Fields marked with an asterisk are mandatory