CONTACT

Work

featuredwork

End-to-end automation of flight operations using MEAN stack

The Problem

Our client wanted the end-to-end automation of flight operations, with a host of custom features.

Our Solution

End-to-end flight operations automation was achieved using MEAN stack. This included booking, crew planning, pilot reports, and various other reports. A modern flexible UI was implemented using Angular. It captured a large set of information from Pilot reports and enabled the dynamic display of crew scheduling.

PROJECT HIGHLIGHTS
Startup – Cloud, Design UX/UI

Machine Learning model that leverages social data to match the right candidates for an open role

The Problem

How could recruiters use social data to get the best candidates for an open role? Instead of relying exclusively on resumes.

Our Solution

We built a Machine Learning model that matches the right candidates to the right job using not just their resumes, but also social data and a number of other parameters such as GitHub activity, LinkedIn recommendations, etc. The same matching algorithm is also used to find ideal jobs for candidates.

The application was completely responsive across desktops, tablets and mobile devices. React (Virtual DOM, Partial Rendering, One Direction Data Flow etc.) was used to mitigate the latency issues with third-party data sources.

PROJECT HIGHLIGHTS
Enterprise – AI/ML, Cloud

Credit cards and auto loan origination for an under-served population

The Problem

An innovative finance company in the US wanted to launch new products like credit card and auto loans to individuals with little or no credit history. They wanted origination and servicing applications, a rapid Go-to-Market (GTM) was essential.

Our Solution

Our in-house design studio worked with the client’s marketing team to design an intuitive system that maximized lead conversions.  We used the latest tech stack (Angular 8 and Ionic) to develop a Progressive Web Application that was responsive, personalized and provided multilingual support (English and Spanish). A highly scalable, cloud-based, microservices solution was built on a DevOps environment that aided quick iterations to market.

PROJECT HIGHLIGHTS
Startup – Cloud

Automated pricing using Deep Learning

The Problem

A large B2B manufacturer was losing sales, because it took human-led teams 7 days on an average for price analytics and discount approvals.

Our Solution

Our application delivered instant quotes using AI, for the first time without human intervention. This reduced discounts and increased quote conversion by about 20%.  The application used historical CRM data,  decision trees, co-occurrence matrix, prediction engines, neural nets, and deep learning.

PROJECT HIGHLIGHTS
Enterprise – AI/ML, Architecture, Cloud

Distributed Supercomputer using Blockchain and Machine Learning

The Problem

Build a distributed supercomputer that incentivizes users for providing the hardware for computation, without the risk of fraud.

Our Solution

We built a Distributed Supercomputer where any computer on the internet running Windows, Mac or Linux could serve as a node. The nodes that are used for distributed computing are clustered using the Expectation-Maximization algorithm which buckets similar nodes into a cluster.

The assignment of a node for doing a computational task is done using a multi-arm bandit simulation. Financial settlements are done using Nebulas, a third-generation blockchain.

For managing jobs, three different schedulers were considered – Kubernetes, Nomad, and Docker Swarm. Finally, Nomad was chosen as it requires no external services for saving its state and stores it on the master node itself. Additionally, it is a single binary that acts both as the master node and the client.

Enterprise – AI/ML, Architecture, Cloud

Design Thinking led product strategy to increase user engagement

The Problem

KissCam’s previous mobile app was not getting enough engagement with users. The app allowed users to capture photos and apply overlays to resemble kiss cam segments in US’ stadium sports events.

Our Solution

We felt that the app was missing out on several potential use-cases and approaches that would boost their customer base and engagement levels. We brainstormed with the client and arrived at multiple use-cases; ultimately narrowing it down to the following:

  • Event listing and contest feature
  • Family-friendly portrayal of KissCam
  • Voting on their favorite entries
  • Event notifications
Startup – Design UX/UI

Using conversational UX and human-centered design for the bottom of the pyramid

The Problem

Chilasa is a non-profit organization. They wanted a mobile app to help rural carpenters negotiate quotes and receive orders from city-based merchants. The catch? The carpenters were semi-literate and had only used messaging apps like WhatsApp.

Our Solution

We used Conversational UX to solve the problem. Carpenters received work inquiries as chat conversations where pricing could be negotiated, orders could be accepted or rejected, and progress updates could be shared effortlessly.

Startup – Design UX/UI

Improving reporting performance by over 90X

The Problem

A healthcare technology provider took an average of 15 minutes to generate patient reports, because of the massive amounts of data (8B+ records). They were using Amazon RDS. This was leading to long wait times and directly impacting customer satisfaction.

Our Solution

We reduced the average report generation time of a healthcare company to 10 seconds, this a 90X performance improvement despite reducing the number of RDS instances by 20%.

To do this, we first identified the performance bottlenecks in the current system using AppDynamics. Then we re-architected the data replication strategy. We optimized encryption/decryption process without compromising on HIPAA compliance. We also made several improvements by implementing real-time data syncing using Kinesis, SQS & MySQL binlog reader.

PROJECT HIGHLIGHTS
Startup – Architecture, Data Platforms & Visualization

Collaborative lead tracking for an automobile manufacturer

The Problem

An automobile company wanted to track sales leads and conversion rates across the manufacturer, dealer and financier networks.

Technical Challenges

A considerable number of dealers were based in rural locations of developing countries. They had very poor internet and mobile connectivity.

Our Solution

A mobile app was developed for the dealer in React Native while the manufacturer and financier web applications were developed in React. Isolation of component rendering from API calls was done to ensure fault-tolerance even in low-speed 2G networks. Multi-language support was provided through Internationalization (i18n).

Enterprise – Architecture, Design UX/UI

Gamified platform that delivers extreme performance and scalability using microservices architecture

The Problem

KissCam wanted to build a highly engaging and gamified platform for conducting photo contests at sports arenas and large events during breaks. Users can click photos or shoot videos, quickly add one of the many frames available in the app and post to social media. Other users then vote and select a winner.

Technical Challenges

Since the action happens suddenly in just a few minutes of a game, the server-side needed extreme performance and scalability.

Our Solution

Android and iOS apps used image optimization and resolution based photo uploads. We used microservices to scale each service individually. We also implemented auto-scaling in AWS ECS to scale the application without any downtime. Performance tuning was done for scaling the application to handle huge and sudden loads. We also built a cloud storage platform for KissCam users to store media files and scaled the application to support huge arenas to the tune of 50K simultaneous users.

Startup – Architecture, Cloud, Design UX/UI

Intelligent B2B prospecting

The Problem

There has been an explosion of retail companies built around products like Shopify. However, it is very hard to sell to these companies as there is no public data available around these companies.

Our Solution

The system we have built has collected over 5 million company names and 8 million contacts. We continue to add 10,000 data daily and we are looking to reach 1 billion data points (which is about 30 million companies) in the next 6 months.

Firm-specific data from several disparate sources is first collected. An ETL process with NLP techniques is used to normalize the data to a unified company and person profile. A recommendation algorithm predicts and recommends the companies that fulfill our targeting criteria. To get sales folks to use it, we ensured the UI was simple, powerful, and fast. We chose React + Flux. We introduced messaging-based interactions instead of forms where possible.

PROJECT HIGHLIGHTS
Startup – AI/ML, Architecture, Cloud, Data Platforms & Visualization, Design UX/UI

Trading platform to propose fund and settle transactions

The Problem

The financial services mobile app was required to handle complex on-boarding processes and transactions.

Our Solution

We shipped a supply chain financing platform with complex user and company on-boarding process, and trading platform to propose fund and settle transactions. On-boarding widgets were implemented using Angular.js.

Startup – Cloud

Location tracking of services rendered for fraud prevention

The Problem

A fast and easy-to-use mobile app for field personnel to validate their service visits.

Our Solution

We used Angular.js and jQuery to develop a mobile app with a responsive UI, so that field teams could also use it on a tab. OpenStreetMap (OSM) was used for mapping core data because it’s free and is used by the likes of Foursquare and Evernote. For mobile-friendly interactive maps, we chose Leaflet as it is lightweight and fast.

PROJECT HIGHLIGHTS
Startup – AI/ML, Architecture, Design UX/UI

Daily deals from retail stores, restaurants, multiplexes and more

The Problem

A deal-aggregator app that drives traffic to physical retail businesses

Our Solution

Never miss out on a striking deal, as SnapMap brings you daily deals from retail outlets, restaurants, multiplexes and more. Once you’ve made the deal and enjoyed the service, you can rate and share it with anyone. If you’re a service provider, lead users directly to your deals with SnapMap and drive sales like never before.

Startup – Architecture, Design UX/UI

Mobile-delivered workouts

The Problem

Build a platform that allows both iOS and Android apps with minimal changes.

Our Solution

Power 20 follows a single pattern across its 14 different applications. The application has been built from ground-up to work with data from the server without any local setting. A single codebase/package is compiled and deployed with different configurations to enable 14 applications per platform for a total of 28 applications on iOS and Android.

Any new applications can be added by only including a configuration file on the server and making the configuration change on the app. Images and media explain the routines and are widely used across the applications. SDWebImage on iOS and Picassa on Android are used for efficient and intelligent media consumption to ensure the least runtime memory footprint. This, along with AFNetworking on iOS and Volley on Android, provide a robust HTTP request mechanism.

Startup – Architecture, Cloud

Exclusive access to live events from mobile camera feeds

The Problem

The client wanted an app that could be be used by an audience to stream camera feeds from live events, so that online viewers could watch the event from unique angles.

Our Solution

This had several challenges.

  • Choosing the right backend server and rendering engine for the Android platform.
  • Rigorous memory management techniques to ensure the best possible stream quality.
  • Working on Bare Metal Android Canvas code to efficiently handle the incoming video feed.
  • Intelligent switching between supported protocols (RTSP, RDP and HTTP/HTTPS) based on the connection type (LAN, WAN).
  • Handling network switching scenarios and high latency use cases.
  • Some video feeds had four videos stitched together. Slicing of individual videos in such cases had to be done quickly and efficiently.

After considering several streaming and content rendering engines, we finally fixed chose Android Streaming API for implementation. The API had a plethora of features and support for both Android SurfaceView and Bare Metal OpenGL rending canvas for future scaling.

We also built a robust asynchronous HTTP request component based on the Android Volley library to achieve reliable communication between EventStream REST services and the Mobile Endpoint.

Startup – Architecture

Productivity and event scheduling app

The Problem

Calendar apps rarely have any other function, while productivity apps do not have the features to carry out several kinds of tasks..

Our Solution

This app gives users the options to schedule their day, share daily plans, organize events like birthday and promotion parties, invite friends, conduct polls, and chat within a group. They can also sync their entire list of Google, Yahoo, and Group Agendas calendars and keep a tab on all future events.

PROJECT HIGHLIGHTS
Startup – Cloud, Design UX/UI

Collaboration platform for sports events organizers and facility managers

The Problem

Sports event organizers are always looking for suitable venues, which are operated by facility owners. And there are players who want to participate. How do we connect all the three on a unified platform?

Our Solution

GameDay is a social network for sports enthusiasts that connects sports tournament organizers, facility owners, and players. We contributed ideas to break the initial chicken-egg problem that marketplace apps have.

PROJECT HIGHLIGHTS
Startup – Architecture, Cloud

Natural Language Processing (NLP) for discovering enterprise events

The Problem

Large enterprises need a way to keep track of all the events across their IT ecosystem.

Our Solution

Interesting enterprise events happening all across your IT ecosystem are converted into a live stream of events organized around Topics. Real-time analytics engines take action on these events like intelligent routing. For UX, we leveraged the principle of 20% of actions are performed 80% of the time. We enable this 80% via messaging, we built a Slack-like front-end using Angular.js and jQuery.

Startup – AI/ML, Architecture, Design UX/UI

Generating audience analytics for a multichannel YouTube network

The Problem

Our client had around 200 YouTube channels that covered 3 brands. They wanted to track over 2000 such brands for which only shallow data was available.

Our Solution

We crawled millions of records to fetch data on audience analytics, with cross-linked data from G+ & Facebook. We then used Coefficient Correlation and Linear Regression to deliver analytics for 2000+ brands, using videos that covered just 3 brands.

Startup – AI/ML, Architecture

Modelling and visualization of Credit Default and Interest Rate Swaps

The Problem

The client wanted a unified interface to view Credit Default and Interest Rate Swap analytics.

Our Solution

We extracted, translated and loaded the data from three different sources. We built custom models using Python, which was then applied to the crunched data. The resulting predictions were visualized using D3.js.

PROJECT HIGHLIGHTS
Startup – AI/ML, Cloud, Data Platforms & Visualization

Determining clinical events timeline from a Doctor’s notes using Natural Language Processing

The Problem

Many medical events are buried in the notes made by doctors in multiple documents, with many of them having only partial descriptions. As a result, the timeline of significant clinical events is not easily determinable.

Our Solution

We identified medically significant events like ‘infections’, ‘antibiotics’, ‘surgery’, ‘x-ray’, ‘lab test’, and more. We then leveraged NLP to arrive at the occurrence time of significant events by identifying temporal expressions like ‘today’, ‘two weeks ago’, etc., extracted from the multiple documents and correlated them with the date of document creation. We then stored this data in a structured repository for easy retrieval to construct the timeline graph of the significant clinical events.

Enterprise – AI/ML, Cloud

Improve the prediction of losses due to mortgage delinquency using Machine Learning and Augmenting Customer Data

The Problem

Accurately predict losses due to mortgage delinquency using available data points.

Our Solution

A popular short term lending portal empowers mortgage brokers to compete with banks and large retail lenders, by providing predictive technology and tools. Its CoreLogic model predicts pre-payments and loan defaults. We did the segmentation to increase the accuracy to predict delinquency of a loan using credit bureau data, customer transaction data, and customer behavior data. A GBM model was built to predict the front-end debt-to-income ratio (FEDT), which is key for predictive delinquency.  Further, we experimented with 160 variations of GBM models with Machine Learning techniques using the Caret package. Various visualizations were also done to compare the actual data set and the predicted data set.

Enterprise – AI/ML, Data Platforms & Visualization

Simple, patient-friendly clinical narratives with Natural Language Processing (NLP)

The Problem

Doctors and Medical Specialists use domain-specific vocabulary in their clinical narratives to ensure preciseness, this is required for other practitioners. Patients too want to understand their health condition, diagnosis and prognosis; but find their clinical narratives intimidating and difficult to understand.

Our Solution

We created a dictionary of medical terms and abbreviations from existing documentation for specific domains in healthcare. We then parsed the clinical narratives and used Natural Language Processing to ensure the grammatical correctness of the simplified narrative.

Enterprise – AI/ML

Using Deep Learning to help consumers get the best deals from local stores

The Problem

It is very laborious for shoppers to find the best price of a product from the various online and physical stores, as each of them price the same product differently.

Our Solution

Data Science was used to track, predict, and forecast prices based on various factors. We built an application in Ruby on Rails that lets shoppers pick the best prices for products from highly popular Australian stores, such as Coles and Woolworths. The app delivered great user experience by leveraging React for the web and React Native for mobile. We also designed a search algorithm to scan product catalogs using Word2vec Deep Learning neural network and identified the cheapest product by geo-location.

Further, we simplified purchase decisions by comparing prices across brands, regions, and retail branches by predicting a product’s price (using logistic regression models) for the next 30 days. The shopping application also presented actionable insights using D3.js for visualization.

Startup – AI/ML, Data Platforms & Visualization

Reducing patient readmission risk with Machine Learning

The Problem

Hospitals are liable for penalties if the 30-day readmission rate crosses a specified threshold for a particular clinical condition.

Our Solution

We analyzed the past patient history of readmissions. Then, we clustered patients based on clinical, social, and behavioral factors like associated clinical conditions, age, gender, weight, lifestyle, ethnicity, economic indicators, geography, etc. With this data, we derived a Machine Learning model to predict the risk of readmission for a patient. Finally, we tested the model on the testing data set, fine-tuned it for accuracy, and successfully ran it across new patients.

Enterprise – AI/ML

Cloud security by detecting event log anomalies using Machine Learning

The Problem

A cloud security provider wanted to detect anomalies and abnormal peaks in outbound traffic.

Our Solution

We set up a continuous feed of raw data logs, using AWS Kinesis from AWS CloudTrail. Data were then grouped by Time, Usertype, and Logtype into multiple batches. From these batches, variables were generated to be fed into a Machine Learning model that predicted if the data entry was an anomaly, using logistic regression.

Startup – AI/ML, Cloud

Identification of fake social profiles by analyzing terabytes of social networking data

The Problem

To determine the authenticity of a social profile.

Our Solution

The client provides a social identifier, a free web identity credential controlled by the user. We designed and implemented an algorithm (based on research from Stanford University) on Hadoop using PIG, to evaluate the authenticity of an individual’s profile attributes. We also implemented various fraud detection and prevention solutions with viral social features to enable users to leverage their social graph, to add to their assert score.

Startup – AI/ML

Contact Us

  • contactus@ideas2it.com
  • careers@ideas2it.com
Copyright © Ideas2IT | All Rights Reserved
  • Blog
  • Resources
  • Platforms
  • JSNuggets
  • LinkedIn
  • Facebook
  • Twitter

USA

7260 W Azure Dr
Suite 140-603
Las Vegas
NV 89130

India

147 Pathari Rd
Thousand Lights
Chennai 600006
Tamil Nadu

Contact Us

  • contactus@ideas2it.com
  • careers@ideas2it.com

USA

7260 W Azure Dr
Suite 140-603
Las Vegas
NV 89130

India

147 Pathari Rd
Thousand Lights
Chennai 600006
Tamil Nadu

  • Blog
  • Resources
  • Platforms
  • JSNuggets
  • LinkedIn
  • Facebook
  • Twitter
Copyright © Ideas2IT | All Rights Reserved
Privacy Policy
contact us
  • BECOME OUR CLIENT
  • PARTNER WITH US
  • JOIN US

        • We had a FAB 2020 | See our 2020 updates
        • Refer friends and earn CASH | REFER NOW
        • We found and fund companies | Know more about our EiR Program
        • Stay protected from FAKE JOB OFFERS | Learn More
        • Ideas2IT partners with IN-D.ai to provide seamless Documents to Data to Decisions Automation
          KNOW MORE