Overview: Our client is a European MedTech start-up focused on the detection of cardiovascular anomalies. The start-up&rsquo;s objective is to challenge the market for ECG signal-based detection of heart pathologies, such as, but not limited to, atrial fibrillation, premature beats, subventricular tachycardia, etc, obtained from affordable wearable devices such as the Polar H10. The company required an ML-based model development and preparation for the Class 2A medical device certification, in order to ensure that their system is safe and effective for patients to use at home.&nbsp;

Team: Our team of experts included a Data Engineer, Data Scientists, ML Engineers and a Project Manager

Approach:&nbsp; 
Discovery phase

Our Data Scientists collaborated with the client in order to understand their existing ECG signal processing system, as well as their computation-based algorithms. We created an automated testing tool that assessed the performance of the current solution against a range of internal and external medical data sets. Based on this analysis, we provided recommendations to improve the scope of detectable medical conditions and identified areas for improvement.&nbsp; 
We advised the client on the certification process and prepared an action plan for the &nbsp;ML-related work and documentation needed for the Class 2A certification. We also provided improvement recommendations and execution support, which helped the client enhance their ECG signal processing system and algorithms. Our team completed the analysis and recommendations in less than 8 weeks, providing actionable advice, which helped the client reduce the application processing time.&nbsp;

ML-based signal processing model development phase

The client provided the raw ECG signal data, including labelled data with annotations of R-peaks, pathologies, as well as &lsquo;soft&rsquo; and &lsquo;hard&rsquo; noise segments. This labelled data was used as inputs for the models and deemed as their training set. The quality and accuracy of pathology predictions (detection) heavily depend on the cleaness of the ECG signal. This is why it is important to have robust, well-performing models in terms of accuracy and precision, which can distinguish between the clean and noisy parts of the ECG signals. Our Data Scientists developed ML-based models for &lsquo;soft&rsquo; &nbsp;and &lsquo;hard&rsquo; noise detection. Upon successfully passing the strict model performance acceptance criteria of the client, our ML Engineers created the production pipelines for training and inference and integrated it into the client&rsquo;s platform and business processes. Our collaboration continues with the development of further pathology detection ML-based algorithms.&nbsp;

 
<iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/Bk_rwYkArs0?si=hetzAi2ffZkTg34N" width="560"></iframe>

AI model development and certification for cardiovascular medicine

Overview:&nbsp;Our client, a financial services company, approached us with a challenge to improve their data analysis tools and provide automation to their team&#39;s daily work. They wanted a solution that would help their surveillance organization gain more insights into potential scenarios. Our approach was to create a solution that would enable them to predict MTD/YTD prices.

Approach: We worked in close collaboration with the client to analyze multiple numerical methods and compose different types of feature vectors to improve the prediction model&#39;s accuracy. We developed a script that extracts information and an algorithm that calculates the analysis of historical price changes. 
We integrated multiple data sources into the solution, including the Bloomberg service terminal, to ensure we had the most accurate and up-to-date data. We developed an API and a user-friendly interface for filtering and searching the information we extracted and analyzed. We used Keras to predict MTD / YTD prices developing a stock prediction model with a neural network to predict the returns on stocks.&nbsp;

Tech stack: Python, Django,Vue.js, AWS, Keras.&nbsp;

Stock market data tool integrated with Bloomberg

Challenge:&nbsp;Creating a fully functioning solution from scratch 
 
Team:&nbsp;Data Engineers, Data Scientists, ML Engineers,&nbsp;DevOps 
 
Solution:&nbsp;The project started with the investigation phase to analyse the existing data and test multiple solutions which meet the needs of both client and cloud providers. AWS was selected as a core service provider for data storage combined with ElasticSearch.&nbsp;Our team built the full ETL process to start operations. Once the data structure and pipelines were set, we introduced two teams of Data Scientists - one specialized in semantic analysis (NLP) and the other with experience in image recognition. The ML part was further taken care of by our engineers. The output was a dashboard of data visualisations made in Kibana to present the results. 
 
Status: Successful completion of the data engineering phase with ongoing data science stages.

Image recognition and NLP for fraud detection

Challenge: The client`s request involved road and traffic analysis. The task included building a vehicle counting system based on vehicle type and classification, as well as differentiating between various types of vehicles and conducting a total count.

Approach: We started by developing a custom video surveillance software which made it possible to remotely watch the traffic situation and collect data. Utilizing image recognition and data analytics techniques we developed a POC model analysing the traffic data, which was further extended to a fully functioning tool for road and safety as the traffic analysis.

Through advanced deep learning our team created a solution which was able to detect and alert for potential accidents, predict congestion, or plan efficient roads and parking spaces. The solution is currently growing into autonomously monitoring traffic cameras and systems and generating real-time alerts when certain events of interest occur.

Tech stack: Python, React.JS, Yolo, SSD and OpenCV

 
&nbsp;

Traffic analysis and prediction based on AI

Overview: Our client needed a tool to analyze electricity consumption based on the data from sensors integrated into electrical sockets, in real-time and historically, with the ability to track any critical moments. The client also required the tool to be scalable and applicable to other sensors in the market.

Solution: To ensure that the tool met the requirements, our team collaborated with the client&#39;s team to understand their needs and preferences. We analyzed the data collected by the sensors to develop algorithms to accurately track the electricity consumption of each socket. We then integrated the algorithms into a user-friendly interface that allowed users to easily track their electricity usage over time. We used Python, Django and Angular to develop the backend and front end of the tool, respectively, ensuring a scalable solution that could be easily extended to support other sensors in the market.

Our team also implemented various features to enhance the user experience. We included notifications and snapshots for critical moments, such as extreme power consumption, electrical fault or a sudden surge in electricity usage. We also generated heat maps for each socket, providing users with visual information about their electricity usage over time. We ensured that the tool was responsive and could be used on mobile devices, enabling users to monitor their electricity usage on the go.

Tech stack: Python, Django, Angular, AWS.

IoT tool for electricity consumption analysis

Research led by Georgi Nalbantov PhD, Head of Data Science @ VectorLabs.AI, to examine the impact of pre-existing cardiac conditions on radiation-induced lung toxicity (RILT) after high-dose radio(chemo)therapy for lung cancer. 
 
Overview:

<ul>
	<li>Traditionally, radiation effect on the heart and lungs were studied separately</li>
	<li>Recent studies reveal a short-term interaction between heart irradiation and lung dysfunction</li>
	<li>This study bridges the gap by investigating how cardiac issues affect RILT in the short term&nbsp;</li>
</ul>

Observations:

<ul>
	<li>28.9% of patients had cardiac comorbidity before radiotherapy</li>
	<li>44% of patients had cardiac comorbidity before radiotherapy</li>
	<li>Patients with cardiac comorbidity had 2.58 times higher odds of developing RILT</li>
</ul>

Predictive model for RILT:

<ul>
	<li>A model was built which helps identify patients at higher risk of RILT</li>
	<li>This model incorporates cardiac comorbidity, tumour location, lung function, chemotherapy, and pretreatment dyspnea score</li>
	<li>The model demonstrated an Area Under the Curve (AUC) of 0.72 in the training set and 0.67 in the validation set, signifying its predictive performance 
	&nbsp;</li>
</ul>

&nbsp;

&nbsp;

Research Overview: Cardiac Comorbidity and Radiation-Induced Lung Toxicity (RILT)

Increased CLV through a personalised customer-centric approach.

<h2>Executive summary</h2>

Traditional banks face several challenges in the modern banking landscape. These challenges arise due to the changing expectations of customers and the rapid advancements in technology.

To address these, banks must embrace innovation, invest in technology and talent, prioritize cybersecurity, and maintain a customer-centric approach while navigating regulatory requirements.&nbsp;

All-encompassing strategy formulation and adaptable, coherent execution are key to thriving in the dynamic banking landscape. 
&nbsp;

<h2>The important questions</h2>

<ul>
	<li>How likely is the client to purchase a product?</li>
	<li>How profitable is it to approach a customer with a specific offer?</li>
	<li>How to increase cross-sell and up-sell?</li>
	<li>How can we improve response rates to direct marketing campaigns?</li>
	<li>How to transform each contact into a sales opportunity?</li>
</ul>

<h2>&nbsp;</h2>

<h2>Challenge description</h2>

There is a trade-off of the goals between the Marketing and Sales and Risk Departments.

Risk Department is incentivized to keep the risk levels low and to avoid customers with higher chances of default.

Marketing and Sales Department on the other hand, benefits from higher number of high-end products sold. This leaves out:

<ul style="margin-left:40px">
	<li>Willing clients that are deemed risky by the Risk Department (only based on Risk features);</li>
	<li>Clients that are accepted by the Risk Department but are deemed to be non-interested by the CRM (only based on CRM models)</li>
</ul>

<h2>&nbsp;</h2>

<h2>The customer lifecycle view</h2>

<img alt="" src="https://s3.childish.ai/uploads/ckeditor/2023/11/07/lifecycle-view.png" style="height:510px; width:847px" />

<h2>How is it done?</h2>

<ul>
	<li>
	<h3>Customer Lifetime Value&nbsp;</h3>
	</li>
</ul>

All steps listed below, when executed in combination lead to a higher CLV with an increased NFI.

<ul>
	<li>
	<h3>Personalised offering, Next Best Action, Personalised Marketing</h3>
	</li>
</ul>

The Next Best Action&nbsp;algorithm is used to predict the best ways and times to deliver enhanced customer satisfaction resulting into higher campaign response rate and deal closures. As an additional step, algorithms for personalized offerings can be incorporated into the system.

<ul>
	<li>
	<h3>Next Best Offer</h3>
	</li>
</ul>

NBO increases revenue by predicting the most relevant products or services and up-sell/co-sell opportunities to individual customers.

<ul>
	<li>
	<h3>Net Financial Impact</h3>
	</li>
</ul>

The models maximize the Net Financial Impact obtainable from the customers meanwhile considering the applicable risk limits.

<ul>
	<li>
	<h3>Propensity to buy, Probability of Default, Expected Loss, Expected Profit, Customer Churn, Fraud Detection, and Customer Segmentation</h3>
	</li>
</ul>

PtB models enable the expansion and optimization of credit portfolios in competitive and saturated markets by calculating the likelihood, that customer will buy a product or a service. The solution takes into consideration further inputs and constraints.

<h2>PtB-driven solution</h2>

<h3>Current state</h3>

<img alt="" src="https://s3.childish.ai/uploads/ckeditor/2023/11/07/current-state.png" style="height:402px; width:300px" />

The traditional lending process 
The traditional preapproved credit sales process consists of two steps:&nbsp; &nbsp; &nbsp; &nbsp;

<ol>
	<li>setting the preapproved limit by the Credit Risk department&nbsp;</li>
	<li>targeting the offers by the Sales/Marketing department</li>
</ol>

This approach leads to two thresholds.&nbsp;

&nbsp;

<h3>&nbsp;</h3>

<h3>Future state</h3>

<img alt="" src="https://s3.childish.ai/uploads/ckeditor/2023/11/07/future-state.png" style="height:476px; width:300px" />

&nbsp;

Suggested approach&nbsp; 
Considers simultaneously information from both the Sales/Marketing and Risk departments. This allows for customer targeting by risk-adjusted expected profit, thus increasing the overall profitability and size of the credit portfolio over its lifecycle.&nbsp; 
&nbsp;

<h2>&nbsp;</h2>

<h2>What are the benefits of the suggested approach?&nbsp;</h2>

<ul>
	<li>Higher Net Financial Impact (NFI) for the bank</li>
	<li>Prolonged Customer Lifetime Value (CLV)</li>
	<li>Enhanced Customer Experience</li>
	<li>Improved Efficiency and Productivity</li>
	<li>Data-Driven Insights and Decision Making</li>
	<li>Regulatory Compliance</li>
	<li>Personalized Marketing</li>
	<li>Automatization of Loan Application &amp; Approval Process</li>
</ul>

Point of View: Opportunities for AI adoption in Banking

Overview: The Client was in need of our expertise to develop an interactive online platform for historical education centred around the survival stories of prisoners in the concentration camps during the Communist era in Bulgaria. The general idea was to allow the users to have a virtual video conversation with the survivors by asking questions and receiving the

best answer from a pre-recorded set of answers to the most popular questions. They had drawn inspiration from a similar project about stories from Nazi-Germany concentration camps, but they didn&#39;t have the technical know-how on how to achieve it. A similar platform can be seen <a href="https://iwitness.usc.edu/dit/pinchas#haveaconversation" style="text-decoration:none" target="_blank">here</a>. We worked in cooperation with multiple teams engaged with filming the interviews, video processing and graphic design. 
&nbsp;

Solution:

Phase 1 - Planning

We started with thorough planning of the questions for the interviews and the recording process since the team had only a couple of days to spend with each person and there was no room for mistakes. Every person had to be interviewed according to a prepared script and asked a very specific list of more than 500 questions such as &quot;What is your name?&quot;, &quot;What is your favourite colour?&quot;, &quot;What do you remember about World War II?&quot; and others.

Phase 2 - Data preparation

The video post-processing team took the challenging task to cut and edit the raw videos into a set of several thousand video answers. Our job was to categorize all of the video data by a weighted keywords approach and implement an algorithm that would match the keywords in the user question with the categorized answers in the database.

Phase 3: Algorithm development

Taking into account the grammar specifics for the English and Bulgarian languages, we made several configuration iterations to adjust the weights of the keywords and improve the performance of the algorithm. A team of internal and external testers helped to verify the results by trying out a large number of questions with different wording variations. All of the tests were monitored and actively used to constantly improve the algorithm.&nbsp;

Once the platform recorded enough real-user data, the plan was to introduce an AI language model to allow for even more realistic and insightful conversations with the survivors. We would still use the keyword-matching algorithm to compare and measure the AI model performance, which would need significantly more data than we initially had at the start of the project.&nbsp;

Phase 4 - Website development

When the algorithm was ready we continued with integrating it into the rest of the platform where users can log in, keep track of previous chat sessions and find out interesting information and facts about that particular historical period for further evaluation. 
&nbsp;

&nbsp;

Video platform and chatbot for historical education museum

Overview: A retail bank faced the challenge of optimizing offers to attract new clients and upsell existing clients. The marketing and risk departments were working with different approaches, and there was a need for a unified score that could provide a single measure of expected profitability per client. To address this challenge, our data science team was tasked with developing an AI solution that produces a robust objective score for the expected profitability per client, based on both marketing and risk factors.

Solution: Our team developed a CRM (Customer Relationship Management) model that combines marketing and risk factors to evaluate the expected profitability of each banking product based on our developed methodology product. The model uses Propensity-to-Buy (PtB) models to predict the likelihood of a customer purchasing a specific product, and Probability of Default (PD) models to estimate the risk of the customer defaulting on a loan. The output of the model is a single measure of expected profitability per client, which can be used to rank the Next-Best-Offer (NBO) for each customer.&nbsp;

To develop the CRM model, we first collected and integrated data from various sources, including transactional data, demographic data, and customer interaction data. We then applied various machine learning algorithms, such as logistic regression and random forests, to train and test the PtB and PD models. We also conducted feature engineering and selection to identify the most relevant variables for predicting profitability.

A CRM model for effective customer offer optimization in retail banking

Overview: 
Sika Strength, a cutting-edge health, and lifestyle company, aimed to enhance athletes&#39; performance. Specialising in tailored training programs, they sought a technology partner to build an app that could empower athletes to excel. Sika Strength&#39;s team was knowledgeable and throughout the whole process contributed with domain knowledge, including insights into fitness training methodologies, exercise routines, and user preferences, enriching the app with authentic and effective training content.&nbsp;

Challenges: 
A primary challenge was creating an app that is robust, and scalable, incorporating an AI-driven chatbot with no hallucinations while delivering an interactive, user-centric experience. The mutual inspiration between the teams catalysed creativity and dedication.

Solution: 
CHILDISH.AI&#39;s dedicated team crafted the entire app, featuring advanced functionalities and an interactive chatbot powered by generative AI. The model leverages trained data to analyse datasets, proposing optimal responses. The chatbot streamlines customer support, enriching the user experience. Together, we&#39;ve sculpted a seamless, intelligent training companion, harmonising CHILDISH.AI&#39;s technological prowess with Sika Strength&#39;s dedication to healthy living and sports.

Team: UX designer, front-end Developers (React &amp; React Native), back-end Developers (Python &amp; Django), Data Scientists, Solution Architect, QA, and Project Manager. 
&nbsp;

Empowering athletes: crafting success with the Sika Strength App

Challenge:&nbsp;The client, a multinational pharmaceutical company wanted to refactor an existing system for enquiry management and improve its performance and analytical capabilities through AI. The goal was to&nbsp;ensure a consistent customer experience across multiple locations.&nbsp;

Industry: Healthcare&nbsp;&nbsp; 
 
Approach:&nbsp;Our team used semantic analysis with NLTK preprocessing to create different feature extraction and drug product labelling over already accumulated and classified еnquiry data. Preprocessed data were used to train Keras with the TF engine, and evaluated versus built-in SVM algorithms in SKLearn. Results were accuracy near 80% for classification. ML components were integrated into the auto-assign pipeline based on product and team recognized in free text еnquiry.

From a business perspective, the complete solution speeds up the process of enquiry management and&nbsp;contributes to overall customer satisfaction and increased operational efficiency.&nbsp;

Tech stack:&nbsp;Python and Angular developers, Data Scientists, ML Engineers, Project Manager.

NLP development for a pharmaceutical company

Overview: The client was a start-up solving the problem of managing numerous processes within a recruitment department. Hiring teams have data from a variety of sources, which are difficult to process and analyze. Our task was to structure and develop a data structure and create an AI tool for screening candidates. 
 
Approach:&nbsp;Our team of data engineers, data scientists, and ML engineers started with a research phase to understand the client&#39;s requirements and identify the best approach for the project. We conducted a thorough analysis of the recruitment data landscape and the different types of data sources used in the industry. We then developed a solution architecture that could handle the complex data structures and AI models required for the project. We selected AWS as the primary provider for data storage and combined it with other ETL tools to work with different formats from multiple sources.

Once the data structure and pipelines were set up, we used semantic analysis with NLTK preprocessing to extract the necessary information for each candidate. The semantic analysis allowed us to identify the candidate&#39;s skills, experience, and education from their resume, cover letter, and social media profiles. We then developed the ML model using Keras, TensorFlow, and SKLearn to sort the candidates into predefined groups and factors, such as experience level, job title, and location. The output was presented in a structured database of candidates, which could be easily searched and filtered by hiring teams.

AI screening tool for a recruitment software

Challenge: The task was to develop a solution for task management in production companies combined with extracting data from production machines through sensors and PLCs. 
 
Team: Python developers, Angular developers, Data scientists, Computer vision experts, QA experts, DevOps, UX designer and PM 
 
Solution: The solution was successfully developed for the MVP phase and continued to include computer vision combined with tasks, procedures and read-only registers from PLC controllers. Currently using Python OpenCV &amp; YOLO object detector integration from IP camera stream to extract workers&#39; movements around specific industrial areas. We collect data first to perform supervised learning in later stages. 
 
Status: Currently, the software is being integrated into 3 production plants in Bulgaria.

Software with computer vision analysis in a manufacturing plant

Overview: The banking industry faces a significant challenge in accurately assessing the creditworthiness of borrowers to make informed lending decisions. Traditional credit scoring models, which often rely on limited information such as credit history, may not accurately reflect the risk of default. To address this challenge, our team was tasked with developing a more accurate and comprehensive model for predicting the probability of default.

Solution: Our team developed a PD (Probability of Default) model that uses a wide range of customer data, including behavioural and demographic data, to predict the probability of default. The model is based on machine learning algorithms that are trained on historical data to identify patterns and correlations between different variables and default risk.&nbsp;

We first collected and cleaned a large dataset of loan applications and associated customer data and used various machine learning algorithms, such as logistic regression and decision trees, to train and test the model. We also conducted feature selection and engineering to identify the most relevant variables for predicting default risk.

The output of the model is a single score that reflects the probability of default, which can be used to inform lending decisions and set appropriate interest rates.

Developing a comprehensive PD model for accurate credit risk assessment in banking

Challenge: Between 2009 and 2013, our Head of Data Science led the AI development and implementation of the <a href="http://www.eurocat.info/" target="_blank">euroCat project</a>, a groundbreaking solution for personalized treatment methodology in radiation oncology. The project involved five hospitals across three EU countries, utilizing the data of their cancer patients with the aim to optimize personalized treatments. The goal was to develop a Machine Learning model that is capable of learning from disparate data sources without centralizing patient data, in a way that preserves patient privacy. You can read more about euroCat in the academic <a href="https://www.sciencedirect.com/science/article/pii/S2405630816300271" target="_blank">paper</a>.

Solution: The solution leveraged Federated Learning (which has become the more common name for distributed learning) - a technique that enables multiple parties to collaborate on a Machine Learning model without sharing sensitive data and without the need for data to be centralized, via exchanging only model parameters during the learning process. 
In this approach, each hospital trains part of the model at each iteration using its local data and then shares only some parameters with a central server. The central server then aggregates the parameters from all countries to update the global model without accessing the local data. The learning continues through iteration cycles until model convergence criteria are met. The role of a &ldquo;central server&rdquo; can be played by any of the hospitals on the grid. Georgi Nalbantov&rsquo;s AI team used Federated Learning to learn Support Vector Machine (SVM) models, using the Alternating Direction Method of Multipliers (ADMM), from disparate databases to predict treatment outcomes: which can be either a direct treatment effect or a treatment side effect, for example, shortness of breath after (lung) radiotherapy.

 
The performance of the SVM models was evaluated by the Area Under the Curve (AUC) in a five-fold cross-validation procedure (training at four sites and validation at the fifth). The performance of the pooled (federated) learning algorithm was compared with centralized learning, in which the datasets of all clinics are combined in a single dataset. The result of the centralized model was (naturally) the same as the federated-learning model, as they are mathematically yielding the same result.

Federated Learning for personalized healthcare prediction models in oncology

Overview: SpareFare is a UK start-up connecting people who have bought a flight ticket or a hotel reservation but cannot use it anymore, with people who want to buy a discounted ticket. Their team was looking for a development partner with top-notch engineers to help them build the complex architecture behind their platform. The platform had to include complex transactions between the different users and the back office. 
 
Solution: When we joined the project, the client already had an existing platform. The scale-up of the business and the increasing number of clients required to have rebuilt from scratch while keeping the core functionalities and design. Our team had to create a scalable platform, add missing elements and features both in the user interface and the CRM.

The development involved the structure of multiple roles and permissions, payment processing through multiple sources, and payment approvals. The back-office team had to work in a well-structured and quick CRM which we built as a fully custom solution in order to respond to the dynamic requests.&nbsp;

The system also involved multiple integrations with service providers. The biggest challenge was the exchange of constantly changing information about the price of flight tickets. The task required a highly experienced team of developers. Apart from the front-end and back-end development, we supported them with Cloud, DevOps and UX advisory at every step. Our data engineering team was actively involved as well so that the system was ready to grow in a predictive analytics platform in the future. 
 
Team: The solution was built using Python development, React.JS development, Data engineering, UX, DevOps engineering, QA, and Project management.

Web platform with CRM for travel reservations exchange

Overview: One of our clients, an educational company, wanted to create a platform that would engage children in learning and promote reading habits among them. The challenge was to build a platform that had an exciting UX for the children and a complex back-end with multi-level users. The platform needed to allow children to play Q&amp;A games based on books they had read, compete with other children, leave ratings for the book and communicate among themselves and within a group.

Solution: Our team started by developing the MVP and web version with a smaller team. After successfully completing the MVP, we made several major upgrades and the platform expanded to iOS and Android applications. The development process was intensive and required us to work within tight deadlines. Despite this, we delivered a smooth and efficient platform that worked with thousands of students throughout the country.&nbsp;

One of the unique features of the platform was the ability for children to play Q&amp;A games based on the books, compete in teams, leave ratings and comments and communicate with teachers, classmates, family members and other users. This not only made the learning experience more enjoyable but also helped to build a community of young readers. Furthermore, the platform functionalities included a virtual payment system with a custom gateway.&nbsp;

During peak times the platform had over 20,000 users on the site, and it coped with the volume successfully. This was a testament to the scalability and reliability of the platform, which was designed to handle large volumes of traffic. 
&nbsp;

Status:&nbsp;Since the platform&rsquo;s development in 2019, we have developed multiple upgrades and new modules, as well as mobile applications. Moreover, the clients are more than happy and thankful in partnering with us.

Educational gamification platform with mobile applications

Challenge: A manufacturing plant with over 1200 workers was looking for a custom solution to organize their maintenance processes. The existing ERPs did not cover all requirements for the wide range of activities. This had increased maintenance costs and unpredicted downtime.

Client: ABB Bulgaria

Solution:&nbsp;For employees accustomed to filling a lot of documentation which is required both by both management and auditors, the new system was a completely new methodology. Using an agile delivery approach, we took time to define the requirements and listen to the users. The system was based on our Fabrico SaaS with improvements and custom upgrades adapted to the client. Our UX designers and product managers transformed the requirements into the system integrating all custom functionalities in the mobile applications for iOS and Android.

Adding QR code scanners to the existing processes was a disruptive moment and helped the team to increase their productivity and reduce the time needed to analyse data and complete maintenance tasks.

Over one year of operation, the team has already been saving time and having additional security in tracking information on repairs. Emergency repairs were reduced by 10% in a period of 6 months.

Services: Python, Angular, Mobile applications development, UX, QA, DevOps, PM

Maintenance management ERP and storage for an international manufacturing plant

Overview:&nbsp;Our client, a healthcare scale-up, set out to improve their telemedicine platform&#39;s capabilities, enabling patients and healthcare practitioners to connect from a distance using innovative digital-first and high-touch technology. However, the main challenge was to upgrade and expand the platform while ensuring that the tens of thousands of patients and healthcare practitioners already using it could continue to access its functionality seamlessly.

&nbsp;

Team:&nbsp;Our team of experienced Python and ReactJS developers worked together to create a seamless and intuitive platform for healthcare practitioners and patients.

&nbsp;

Solution:&nbsp;Our team collaborated with the client&#39;s existing team to provide support and develop new features for their healthcare app. This app facilitates seamless communication between healthcare providers and patients, as well as other important healthcare stakeholders like hospitals, pharmacies, and healthcare funds.

To ensure the highest standards of privacy and security, our team implemented a comprehensive, HIPPA-compliant workflow that creates a repeatable care plan for each patient and clinical condition. The app offers a wide range of features and interactions, empowering patients to access healthcare services, track their health, and communicate with their healthcare providers with ease.

The app integrates with multiple healthcare devices, which collect and analyze patient data and provide valuable insights to healthcare specialists. With advanced analytics capabilities, the app enables healthcare providers to detect trends and patterns in patient data, allowing them to make better-informed decisions and provide high-quality care.

Despite the project&#39;s complexity, our team successfully tackled regular refactoring and ongoing improvements to ensure a seamless user experience and optimal performance.

&nbsp;

Outcomes:&nbsp;The project was a great success, with the team delivering new modules and functions on time and within budget. As a result, the user base grew to over 100.000 users, and the client has become a trusted partner of the management.

Healthcare app giving full communication between doctors and patients

Overview: One of our clients approached us with the need to develop an innovative and comprehensive educational learning management system. Our team worked closely with them to create a single platform that combines essential features to make it an indispensable tool for educators, parents, and students alike.

The system is designed to provide a seamless and efficient experience for all stakeholders involved in the educational process. Educators can easily track student progress and communicate with parents, while also managing paperwork, tracking special education programs, and implementing the Responding to the Intervention model (RTI).

With the system&#39;s advanced functionality, educators can ensure that each student receives the correct level of support, leading to improved learning outcomes.&nbsp;

Solution: Our team worked closely with the founder of the educational learning management system to fully understand the requirements of educators, parents, and students. We held frequent meetings with the founder to ensure that the platform met their needs and exceeded their expectations. Throughout the development process, we were proactive and inquisitive, asking questions to ensure we were on the right track and providing advice on UX and functionality.

We designed and developed a comprehensive platform that included tailored interfaces for educators and students. The interfaces were designed to meet their specific needs and provide them with a seamless experience. Our team incorporated a wide range of essential features, including progress tracking, parent communication, paperwork management, special education program tracking, RTI model, and Gradebook. We also added additional features like peer assessments for students, Goalbank, and valuable analytical dashboards to provide educators with valuable insights into the performance of their students.

To ensure that the system we built was fully customizable, we utilized Python and Django for the back end, React for the front end and used AWS capabilities.&nbsp;This allowed us to develop a system that could be tailored to the unique needs of each school. Our team thoroughly tested the product at all stages of development to ensure its quality and functionality.

&nbsp;

Tech stack: Python, Django, React, AWS.

Special education learning management system

Overview: Our team was approached by a non-profit organization that focuses on improving the quality of civic education in schools across the country. They were looking for a comprehensive platform that would provide teachers and active citizens with working materials for teaching the subject of citizenship education. 
&nbsp;

Challenge: The main challenge was to develop a user-friendly platform that would allow teachers to quickly and easily generate an activity-filled plan for teaching dozens of curriculum topics. We also needed to ensure that the platform complied with the requirements of the Ministry of Education and provided teachers with a comprehensive set of lesson objectives and activities.

&nbsp;

Solution: Our team developed a resource platform that enabled teachers and active citizens to get a sub-work plan to work on a selected civics topic. We created an intuitive interface for teachers that allowed them to select the audience, choose the section and lesson they wish to prepare, and model how to conduct the lesson. We also included a set of lesson objectives that were compatible with the requirements of the Ministry of Education. Each lesson plan included activity ideas, requirements, and preparation time needed. With the plan thus created, a student sheet could be made. Each teacher was able to see all the generated lessons in their profile.

Case Studies