Predicting a company’s future financial performance
Modulai built a deep learning based system for predicting the values of various fields in a company's annual report - a year in the future.
Currently, there exist ML models to predict different financial KPIs such as debt, profits, revenue, etc. of a company based on their historic values. The values of these fields are related and dependent on each other.
Detecting faulty transmission pole guy wires in drone images
The system consists of deep learning and traditional machine learning parts and is able of screening vast amounts of drone images to detect faulty guy wires.
The objective of the project was to create a machine learning pipeline to analyze images from power lines and detect lack of tension in guy wires. To solve this problem, the team broke down the problem in different stages and created a multi-model AI solution, in close collaboration with the client.Read more
Product recommendations for Ahlsell’s website and app
We helped out with kickstarting the in-house AI capabilities at Ahlsell by collaborating on the development of a recommender system for their website and smartphone app.
In close collaboration with Ahlsell’s data scientists, the team developed an end-to-end pipeline handling data ingestion, data processing, and model predictions. The recommendation system consists of a collaborative filtering model as well as a content-based model.
Bayesian hierarchical model for company credit risk
We developed a credit system to assess the credit risk associated with small to medium-sized enterprise (SME) lending.
The client is an American software company that provides solutions to financial institutions. Their offer includes technology for compliance, credit risk, and lending solutions used to manage risk.
Real-time and In-session: state-of-the-art recommender system for Ahlsell
The Modulai team worked together with Ahlsell’s Applied AI team to develop a real-time session-based recommender system. The system weighs a customer’s intent in a given session on their website or smartphone app to provide contextually relevant recommendations.
In a case like this, careful balancing of model complexity and predictive performance is key to best meet Ahlsell’s needs. Higher predictive performance means customers getting recommendations better suited to their needs, indirectly increasing Ahlsell’s revenue. However, real-time, low-latency inference in the cloud is not free, and customer experience is negatively impacted by slow(er) load times.
Recommendation system for Skincity
Providing accurate skin product recommendations online is difficult. We built a system that combines the knowledge of the skin therapists with product- and customer behavior data to increase product recommendation accuracy with the aim of driving higher conversion rates and customer satisfaction.
The client is an online skincare clinic that offers a finely-tuned selection of professional skin care products and make-up. Central to their operation are the customized product recommendations customers receive from their experienced skincare therapists.
Detecting food intake in glucose time-series from diabetes patients
Together with Digital Diabetes Analytics, we created a meal detection system using glucose level data to help people with insulin-treated diabetes.
Today, more than 5,5 million people worldwide live with type 1 diabetes and need insulin-based treatment to survive. When it comes to diabetes, there’s no “one treatment fits all”, therefore doctor’s need support in optimizing treatments for each patient.
Detecting underlying paroxysmal atrial fibrillation for Zenicor
Together with Zenicor Medical Systems AB, we trained a deep learning model to predict an underlying paroxysmal atrial fibrillation (AF) condition in patients.
Every day, thousands of people suffer from stroke due to an underlying undiagnosed AF condition. Stroke often results in conditions such as paralysis or, in many cases, death. For this reason, precise and early diagnosis of AF is an essential part of stroke prevention.
Predicting when rented equipment will be returned
As one of the largest rental equipment providers in the Nordics and suppliers to thousands of construction sites, this client needed a system capable of predicting when lent out equipment was expected to be returned.
The goal was to optimize the vast logistics chain by minimizing unnecessary transports between their local shops and main warehouses.
Customer feedback clustering using state of the art NLP
Using recent advancements in Natural Language Processing (NLP), the Modulai team developed a model for clustering customer feedback into topics, making it possible to monitor sentiment across these and detect potential negative responses in real-time so that companies can take immediate action.
The client is a Stockholm-based startup founded in 2015 that helps businesses grow by the voice of their happy customers, providing a cloud-based solution for customer referrals, responses, recommendations, rewards, reviews, retargeting, and retention. Staying alert to customer opinion is key since reviews and testimonials are an important part of many companies marketing strategies.
Real-time object detection for online gaming tournaments
Abios Gaming is a startup that focuses on tracking real-time events in online gaming tournament video streams. They asked us to improve detection performance and make previously impossible detections, possible.
Among the objects to be tracked were various weapons and tools the players use in-game, as well as certain interactions. The system detects and tracks timestamped events in correspondence with the objects the players possess, or use, to provide a structured stream of events that captures essential information about the evolution of the tournament.Read more
Personalized recommendations for Lindex
Lindex is dedicated to offer their customers a relevant and transparent personalized experience, in a multi-channel context. To be able to deliver on that front, a robust recommender system is considered a vital cornerstone.
Lindex is a major retailer, active in the Nordics and throughout Europe. They have several million registered customers, and is one of the prominent brands in women’s’ wear, lingerie and kids wear. Nowadays, users expect retailers to provide them with recommendations based on what they’ve clicked on and bought. A feature that both generates more sales and provides the e-shopper with a sense of being cared for.
Intelligent indoor climate solution for real estate developer
Predicting what the temperature will be in a meeting room, 25 minutes into the future.
We used data that had been gathered over a year at the company’s HQ. A combination of temperature, CO2, outdoor temperature, climate system, and meeting room booking data.
Predicting the risk of mission failure in shipments of pharmaceuticals
We applied a set of machine learning techniques to predict the risk of shipment-failure in shipments of temperature-sensitive pharmaceutical goods.
This client is one of the world’s leading providers of solutions for tracking sensitive pharmaceutical goods during shipment and throughout the whole supply chain. Each shipment is tracked minute-by-minute by a temperature logger.
Transaction risk model for a major online payment platform
A team from Modulai trained a model to predict risk direct banking transactions. The project included a full specification of the decision engine infrastructure as well as the deployment plan.
This client is a large fintech in the payments space providing an alternative to credit cards. They process many millions of transactions yearly for thousands of e-commerce sites and online service providers. Each transaction might expose the different parties to various risks, and containing these risks are crucial.
Forecasting the success of fishing trips, for millions of Fishbrain users
Data from 2.5 millions catches was collected and refined. Each data point was annotated with date, time, location, and fish species. Detailed weather information was added to each catch; air temperature, air pressure, wind speed, cloud cover, and precipitation. Temporal data was transformed into astronomical conditions such as moon phase, solar irradiation, and azimuth angle. A global climate model was created,