In the past, Artificial Intelligence was purely R&D. In the past few years, this technology is now present in almost every industrybringing benefits to the businesses that decided to accept it.​ 

We help companies leverage AI to increase revenue

  • By learning relationships from both structured and unstructured data, we help organizations to improve operational efficiency, enhance sales opportunities, and accelerate potential in competitive industries.​
  • By using predictive analytics techniques and developing AI strategies, with data-driven decisions, we transform organizations into strong future-oriented companies.​
  • We provide data scientists and visionaries who bring viewpoints from multiple disciplines, including neuroscience, physics, engineering, computational biology, genomics, and computer science.​
  • ​Our team helps solve challenges in some of the world’s major sectors, including healthcare, retail, finance, and agriculture. ​

Our approach​

Our AI capabilities

We have experience designing, implementing, and automating learning and decision processes.

Data Structures​

  • Heuristic/Implicit Models​
  • Explicit Models​
  • Knowledge Graphs

Data Processing

  • Behavioral Analysis​
  • Probabilistic Attribution​
  • Collaborative Filtering​
  • Time-series Prediction​
  • Named Entity Extraction​
  • Semantic Role Labeling​
  • Inference Engine

Decision Automation​

  • Markov Decision Processes​
  • Finite State Automation​
  • Rule-based Triggers

Visualization​

  • Data Dashboards​
  • Data Simulation​
  • Search​
  • N-dimensional Reports

Our technology platforms​ 

Machine Learning

Our team has expertise in time series forecasting, computer vision, and other statistical machine learning methods, including deep learning. We engineer custom pipelines for feature extraction and modeling across a wide variety of data types (customer, device/sensor, images, etc.).

Natural Language Processing (NLP)

We use state-of-the-art methods to extract domain-specific entities and learn semantic relationships from unstructured text data (scientific literature, patents, product claims, etc.).

Audio and Video Analytics

We engineer audio-video analytics pipelines that quantify human behavior and extract features and digital biomarkers to provide clinical decision support, with applications extending across multiple verticals.

Bioinformatics

We are domain experts in computational biology with technical expertise in biomarker discovery, genomics / GWAS, mechanism of action (MOA), multi-omics, pathway studies, and proteomics.

AI Success Stories

Task

Automatically discover themes from 6 million web articles published daily.​

Challenge

Our client, a digital PR firm, needed to automate the discovery of concepts in new articles published to the web daily, sharing these with their customers, thus driving real-time PR campaigns. Further to this, 6 million articles needed to be processed within 1 hour.

Solution

We built data engineering pipelines to pre-process text strings to lemmatize and drop out stop words. Our team developed a specialized natural language processing (NLP) model to process, classify, and cluster web-based articles based on primary purpose and content. We were able to extract the most common themes present across the full set of new articles. We optimized the performance and parallelized the pipeline to process 6 million articles daily within 1 hour.

Task

Data science to recommend targeted CPG campaigns to maximize ROI and increase sales lift.

Challenge

Our client, a digital marketing platform, enables CPG brands to reach customers via retail locations. The brands need predictive insights on which campaigns are most likely to generate sales lift and ROI, based on past behavior.

Solution

We aggregated point of sale data from 6,000+ locations over three years to identify campaigns based on price discounts.

  • Seasonal sales trends were modeled to identify true sales lift for the campaign.
  • Campaign costs were estimated to generate a campaign ROI and margin.
  • Ensemble machine learning methods were used to learn past campaign behavior to predict sales lift and ROI.

Our client saw a 4x increase in sales leads from a major industry conference based on the newly introduced campaign insights.

Task

Develop predictive models to power the sales process.​

Challenge

Our client is a provider of hotel-inspired services for multifamily communities. When engaging with a new community, their sales team needed to focus and personalize their marketing efforts on the residents most likely to become customers. The ideal outcome was a data-driven way to identify these residents with the potential for high revenue.

Solution

We aggregated multifamily community data and historical revenue. We employed data-science-driven clustering analysis to identify common traits of high revenue customers and trained a model to predict sales outcomes for new communities. Our analysis confirmed that users of our client’s services were much more likely to re-sign the lease, conferring significant savings to multifamily community owners on churn, leading to an acceleration of sales.

Task

Automatically extract & organize information on 250,000+ food products.

Challenge

Our client, a food product data transparency platform, needed to automate the pipeline of data ingestion and quality control of ingredients, brand name, and nutritional facts for food products to ensure food product claims match product ingredients. Data was stored in more than 2 million images of product labels, and they were receiving data on more than 15,000 products per week. The client had OCR algorithms to parse the product label images into text.

Solution

Our team trained a specialized deep learning, natural language processing model to classify and cluster 250,000+ unique products into 2,000 categories of aisle, shelf, and food type. We partnered with the client engineering team to incorporate the data engineering pipelines and classification and clustering algorithms into their internal platform.

Task

Create a video AI platform to analyze human behavior and health.​

Challenge

Our client brings new therapeutics to the market for neurobehavioral disorders, and required a better way to diagnose patients with depression and anxiety based on video and audio content. A platform was needed to enable a digital diagnosis to support patient stratification for clinical trials and to assess the efficacy of treatment.

Solution

We partnered with the client’s data science and software engineering teams to design and build a platform to use machine learning, thus improving the diagnosis of patients with depression and anxiety. Time series audio and video data, captured via a mobile app, were feature engineered to train a model for predicting clinical outcomes. Improved diagnosis will enhance the stratification of patients for trial enrollment and accelerated assessment of therapeutic response.

Task

Build an AI platform to find targets for genetic engineering to improve crop yield.

Challenge

Our agricultural biotech client needed a platform to identify gene targets for desired traits from complex genomic and environmental relationships, based on genome-wide association studies (GWAS), and in the context of current scientific knowledge.

Solution

We used machine learning to identify the association of genomic variants to plant traits. We trained NLP models on a large set of published scientific literature to put variant recommendations in the context of global biomedical knowledge, providing scientists with a better understanding of past studies and the competitive landscape. Early results on crop yields have proven the validity of causal gene recommendations.

Task

Accelerate COVID-19 research with AI-driven insights

Challenge

Natural language processing (NLP) to extract relationships and themes from the evolving COVID-19 scientific literature
The global scientific community has risen to confront COVID-19: there are over 200,000 research publications related to coronavirus, with more than 4,000 added every week. Scientists drawing knowledge and insight from this ever-expanding literature face difficult challenges: tracking synonymous terms for genes and drugs across fields, connecting biological relationships among entities across articles, and distilling the essential information out of large sets of literature.

Solution

We built an open access NLP-based application using the CORD-19 dataset, the most extensive machine-readable coronavirus literature collection available for text mining. Our application includes domain-specific dictionaries for scientific entities including human genes and molecular pathways, viral genes and mutations, drugs and treatments, symptoms, diseases, and keywords. The application provides multiple views on relationships among entities, and our “tl;dr” feature identifies and summarizes the key themes in large document sets. Access the app here: https://www.covid19research.ai/

By submitting your information, you are automatically accepting the Privacy Policy and Terms and Conditions of IT Labs. The information submitted to IT Labs will not be used by our partners and will not be shared to other Companies to be used in Marketing purposes.

CONTACT US

We'd love to

hear from you

Whether you have a question about our services, products, prices, need a demo or you want to join our team, please use the form, and we will respond to your query immediately.
Want to turn data science into business value to your customers?
Use our FREE 1-on-1 workshop