Innowise Group

Native iOS and Android applications serving as a digital wallet for instant payments

The mobile application is integrated with APIs of several major banks of the country. After registration and verification in the app, users get access to their digital wallets. To replenish the account, residents transfer money from their local bank accounts, while tourists just add their bank cards for that. 

Users can make requests for payment (e.g., split a restaurant bill for several people), pay using QR codes, make money transfers to another person by her or his mobile phone number or email. The app also provides information about bank account balances and stores the history of payments. 

Our team worked on backend and native iOS and Android applications, as well as business analysis and quality assurance of the project. The solution is developed in accordance with ISO 20022 standard, uses Swift MT, and integrates RTJS for real-time payments between banks. To protect confidential data, we integrated a security system (TLS 1.2, SSL Pinning, check for rooted devices), used PIN code validation and data encryption. The solution has multi-tenant architecture and thus can be used and tailored to the peculiarities of any bank system. 

Technologies and tools: Java, RxJava, Kotlin, MVVM and Clean Architecture, Coroutines, Dagger 2, JUnit, Mockito, REST, Robolectric, Espresso; Swift, MVP and VIPER, RxSwift, GCD, XCTest, Firebase

The solution enables teachers to organize online school lessons in an effective and interactive way

The online platform created from scratch by our team takes into account all aspects of the learning process and helps to enrich it with new tools and experiences. We aimed to develop a high-load video conference platform with a set of features to simulate real lessons as accurately as possible. 

It helps teachers to schedule, prepare and conduct lessons, store educational materials, invite pupils from different classes or other people to broadcast. Lessons are taught in real-time through a browser with the help of a video conference, so users may connect via any device – PC, tablet, or smartphone. Lots of functions are provided to make the process more interactive – pupils can raise their hands if they want to answer, paint and type on a virtual blackboard, communicate in chat, and take quizzes created by a teacher on the platform. 

While engineering the platform, our development team paid special attention to the stability and security of the solution. Thanks to intelligent server distribution, the system handles high loads and can be scaled up automatically without significant effort and cost. Good connection quality and high speed are realized with geographically distributed network architecture. The system is resistant against OWASP TOP 10 vulnerabilities, connections are protected according to TLS and SRTP protocols. Personal data are stored only in encrypted form, and access rights, including access to view personal data, are strictly delimited. 

The solution has already proved its effective and reliable work for more than 200,000 simultaneous users and is planned to be scaled up soon.

Technologies and tools: Java 11, Reactor, Spring Cloud Gateway, Spring Cloud Config, Vault, Spring Data, Spring Security, Lombok, MapStruct, WebFlux, PostgreSQL, Redis

NLP algorithm helps to analyze the tone of publications about bitcoins to predict changes in the rate of the cryptocurrency

Innowise Group created the solution for a cryptocurrency exchange to make more exact forecasts of the rise or fall of the bitcoin. As its rate movement depends highly on the mood of investors, it is necessary to take into account and rationalize some emotional factors as well. In addition to standard methods of predicting exchange rates, the system analyzes a huge amount of data from social networks and media, correlates them with trading data, and gives a better forecast. 

Our team of Python Developers and Data Scientists used the NLP algorithm that enabled the system to collect and analyze data from Twitter posts that mention the word "bitcoin." Semantic technology processes the logical structure of sentences to identify the most significant elements in the text and understand the discussions' essence. In the next step, the system collects and stores data and then uses analysis to predict changes in the bitcoin exchange rate for a given period (a week or a month).

The advantage of the system is that it is constantly learning. For instance, it can already recognize tiny details such as personal humor or sarcasm, thus making forecasts even more accurate. 

Technologies and tools: Python, spaCy, Gensim, Keras, Scikit-learn.

NLP algorithm helps to analyze the tone of publications about bitcoins to predict changes in the rate of the cryptocurrency

Innowise Group created the solution for a cryptocurrency exchange to make more exact forecasts of the rise or fall of the bitcoin. As its rate movement depends highly on the mood of investors, it is necessary to take into account and rationalize some emotional factors as well. In addition to standard methods of predicting exchange rates, the system analyzes a huge amount of data from social networks and media, correlates them with trading data, and gives a better forecast. 

Our team of Python Developers and Data Scientists used the NLP algorithm that enabled the system to collect and analyze data from Twitter posts that mention the word "bitcoin." Semantic technology processes the logical structure of sentences to identify the most significant elements in the text and understand the discussions' essence. In the next step, the system collects and stores data and then uses analysis to predict changes in the bitcoin exchange rate for a given period (a week or a month).

The advantage of the system is that it is constantly learning. For instance, it can already recognize tiny details such as personal humor or sarcasm, thus making forecasts even more accurate. 

Technologies and tools: Python, spaCy, Gensim, Keras, Scikit-learn.

The solution helps stores to forecast sales and prevent customers outflow, thus optimizing many business processes

Our team created a solution for retailers and online stores which makes forecasts for 5,000+ products. We used accumulated for three years data on daily sales, purchased items, average checks, loyalty card types, promotions, and so on to teach the application to identify seasonality in demand by month and day of the week, determine trends for each product group, and evaluate the impact of discounts and promotions on product sales. Based on this analysis, the program builds sales forecasts for a month, a quarter, and a year and identifies changes in demand for individual groups of customers. The solution increased the accuracy of forecasting for the next three months from 77% to 93%.

Another part of the program calculated the likelihood of customers outflow within 1-3 months. Our Python development team examined many parameters that impact customer activity: frequency and volume of purchases, number of site visits, date of the last purchase, viewed and selected products, positive or negative user experience. We identified groups that are "at-risk zone" and helped the client find out the proper offer, which will motivate customers to make purchases. For instance, we defined the most relevant goods based on the customer's previous purchases and figured out the right time for sending a message. It allowed the store to tailor the communication to each customer's needs and resulted in higher CTR (from 2.8% to 5.1%) and lower churn rate (from 9.4% to 5.6%).

Altogether, the system helped the business retain customers, boost sales through repeat purchases, and optimize business processes such as marketing communication, logistics, and storage of goods in the warehouse. 

Technologies and tools: Python, ARIMA, ARCH, Recurrent neural networks, Prophet; Pandas, NumPy, Scikit-learn.

Custom electronic data capture (EDC) system with a special add-on for portable heart monitors supports the whole cycle of clinical testing

We developed a flexible constructor which allows clinics and hospitals to set and customize all working processes. It helps to create study workflows with special rules and roles depending on user needs. Some clinical groups may have a separate work cycle with specific rules within the study if required. 

Users can create any necessary data collection and reporting forms with all required fields and special validation rules for each of them. For instance, it's possible to activate the task tracker to monitor the status of forms. The system allows flexible customization of the user interface (graphics, placement of elements, etc.). If needed, it's possible to import certain data into the system after checking them for integrity and correctness. Protecting data against alteration and preventing data breaches, all user actions are registered and stored in the audit trail available to the administrator. The system also enables users to generate various reports and export them in XLS, CSV, and PDF formats. 

Later on, our team also created an add-on for cardiac monitors. It allows cardiologists to monitor the condition of patients and prescribe treatment based on data from cardiac monitors. We developed a system of additional protection of personal data, whereby doctors have access to their patients' information only. 

Our team also implemented the Web API, which integrates third-party services such as patient registration systems, records keeping, insurance systems, etc. It allowed to expand the functionality of the app and add new users over time.

Technologies and tools: .ASP .NET MVC, ADO .NET, Devexpress, Devextreme, MS SQL, Azure; .NET Core Web API,  T-SQL, Azure, Cosmos DB, Azure Functions, Dapper, Azure Appication Insights, Azure AD B2C, Azure WebJobs, Azure Datastorage, jquery, RedisCache, Azure DevOps

Native mobile applications for iOS and Android with the Augmented Reality module allow users to witness past events and visit lost historical sites in 3D

Built-in Google Maps and geolocation function help tourists to navigate in an unfamiliar city, as well as show the nearest sightseeing.

When users reach the attraction, e.g. a ruined building or historical site, they can learn more about it by listening to an audio guide, watching a video with past events, or studying 3D models of already non-existent buildings in the format of augmented reality: life-size, in all details. 

The application also lets tourists take a photo with historical characters or objects in AR. Users can download photos and videos for offline access, add to favorites, and share links to them with friends. Thus, the app enriches traveling with new immersive experiences.

The peculiarity of the project was the reconstruction of the archive photos of old buildings and artifacts into detailed three-dimensional models, recreated by our 3D designers and “made alive” by Unity Developers. Our .NET team focused on creating commercial content for the customer. For example, in order to take a photo with an augmented reality object, it is necessary to subscribe to the app and make a payment. The resulting photos can be shared on social media pages, which the user subscribes to during registration.

Technologies and tools: Unity, C#, Mapbox, AR Foundation, Unity IAP 3DStudio Max, 3D-Coat, Photoshop, .NET Core 3.1, WebAPI, MSSQL, EF Core, Azure BLOB Storage, Swagger, Google, Apple & Facebook public APIs, Serilog, Swift, Kotlin, MVP, GCD, Alamofire, Maps/CoreLocation, REST, Firebase (Analytics, Crashlytics, Distribution), REST.