Logo-black

Elevating the student experience with AI-powered search

  • Education

Elevating the student experience with AI-powered search

OneSix enhanced the student experience for a global study abroad organization by developing an AI chatbot powered by Snowflake Cortex Search. The solution ingests unstructured documents and enables natural language search.
AI & Machine Learning
AI Agents & Chatbots
Snowflake

Overview

Facing information overload for students

Supporting thousands of students across hundreds of global programs, a nonprofit study abroad and intercultural exchange organization faced a major challenge: critical information—such as travel logistics, visa requirements, lodging info, and cultural context—was scattered across numerous unstructured sources.

Students struggled to locate critical information, often leading to confusion and repeated questions directed to support teams. The organization needed a centralized, intelligent solution to streamline access to program-specific information and relieve the burden on internal staff.

Our Solution

An AI chatbot powered by Snowflake Cortex

To enhance the student experience and increase operational efficiency, OneSix developed a robust conversational AI chatbot, seamlessly integrated into the organization’s website and powered by Snowflake Cortex Search.

Key Capabilities
  • Document Ingestion & Indexing: The chatbot ingests thousands of unstructured documents, including:
  • Program-specific reading materials (PDFs)
  • Location-based “Know Before You Go” guides (PDFs)
  • Content collected via web scraping
  • Natural Language Search: Students can ask intuitive, conversational questions such as:
  • “Do I need a visa for Seville?”
  • “Will I receive college credit?”
  • “What’s included in the housing package?”
  • “How do I get around?”
  • Real-Time, Reliable Responses: Answers are grounded in the organization’s official documentation, ensuring accuracy and consistency.
Technical Implementation
  • Advanced Chunking & Preprocessing: Custom pipelines split content into meaningful, searchable segments.
  • LLM Prompt Engineering: Carefully crafted prompts optimize answer accuracy, context relevance, and tone.
  • Custom Search Tuning: Retrieval and ranking strategies were tailored using content type and user behavior.
  • Backend Integration: Python-enhanced logic is fully embedded in Snowflake SQL stored procedures and UDFs.
  • Optimized for Performance: Fine-tuned Snowflake Cortex implementation balances cost, speed, and accuracy for enterprise-grade performance.

Results

Transforming the student support experience

  • Reducing support load: Internal teams now rely on centralized, AI-powered search to answer student questions more efficiently.
  • Enhancing the student experience: Students benefit from 24/7 access to trusted information, increasing their confidence and satisfaction.
  • Earning internal praise: Staff report fewer repetitive queries and a noticeable improvement in operational efficiency.

Ready to unlock the full potential of data and AI?

Book a free consultation to learn how OneSix can help drive meaningful business outcomes.

Contact Us

Leveraging computer vision to identify animals at risk of injury

  • Sports

Leveraging computer vision to identify animals at risk of injury

OneSix developed a scalable horse workout tracking application using advanced computer vision, multi-camera arrays, and ultra-wideband tracking to monitor key performance metrics and detect early signs of injury.
AI & Machine Learning
Computer Vision

Overview

A data-driven approach to equine health and performance

A leading provider in the horse racing industry sought to develop a Horse Workout Tracking Application that:

  • Identifies signs of injury before catastrophic breakdown
  • Derives critical metrics e.g., velocity, stride length, etc.
  • Scales to 3,000-4,000 unique horses per track per year

These insights will be used to:

  • Improve animal safety and welfare with early detection and intervention for potential issues that may arise for both the track and the animals
  • Provide trainers and owners with detailed performance metrics and enable them to monitor and visualize metrics

Our Solution

A scalable, real-time injury detection system using computer vision

OneSix built a horse workout tracking application that leverages an overhead multi-camera array, on-track cameras, and an ultra-wideband tracking system to monitor and derive critical metrics from workouts.

  • Installed 7–10 trackside cameras across three unique tracks, along with a complete overhead camera array.
  • Developed a robust production pipeline to fully process footage from on-track cameras, ensuring seamless data collection and analysis.
  • Built an injury detection system capable of identifying foreleg lameness with high accuracy.
  • Horse tracklets are projected to RWC using epipolar geometry to derive key performance metrics such as speed, stride length, acceleration, and symmetry.
  • Real-time alerts are sent to veterinarians via SMS within 3–5 minutes of detecting an adverse event.
  • Alerts are integrated into the RH360 app, allowing vets to review cases and provide feedback.

Results

Proven impact and growing demand

The system successfully identified hundreds of veterinarian-confirmed foreleg injuries, demonstrating its effectiveness in injury detection. Its impact has driven strong demand from veterinarians and industry professionals seeking to enhance equine safety.

Ready to unlock the full potential of data and AI?

Book a free consultation to learn how OneSix can help drive meaningful business outcomes.

Contact Us

Monitoring grocery store shelf inventory with computer vision

  • Retail & Consumer Goods

Monitoring grocery store shelf inventory with computer vision

OneSix designed and implemented a computer vision-based product identification pipeline capable of rapidly identifying products on grocery store shelves.
AI & Machine Learning
Computer Vision

Overview

The complexity of grocery product identification

Grocery retailers rely on accurate, real-time product identification to manage shelf inventory, ensure planogram compliance, and reduce stockouts. However, the diversity of packaging, frequent product updates, and variable image capture conditions make automated product recognition extremely challenging at scale.

Our client, a provider of image-based grocery analytics, needed a robust, scalable solution to power its product recognition AI toolkit and enable high-speed identification from both mobile and robotic capture sources.

Our Solution

A computer vision-based product identification pipeline

OneSix designed and implemented a robust computer vision-based product identification pipeline capable of analyzing high-resolution shelf images and delivering product-level insights at scale. The solution featured:

  • Custom-trained computer vision models to detect, segment, and classify products in complex retail environments.
  • High-speed vector search across tens of millions of product variations to rapidly match images to known SKUs.
  • Rich metadata output, including product IDs and associated SKU-level details.
  • Scalable production infrastructure, incorporating optimized models, graph-based search, and dynamic supporting databases.
  • Comprehensive tooling, enabling internal teams and external customers to deploy product ID endpoints, create and manage product sets, and support new retailer onboarding.
  • Advanced classification methods, including open-set and few-shot learning to recognize novel or rare products and identify out-of-set items for refinement.

Results

Faster, smarter grocery store shelf analytics

The end-to-end solution delivered measurable impact for grocery retailers:

  • Reduced stockouts through accurate identification of missing or misaligned products.
  • Improved planogram compliance via automated shelf verification from various image capture methods.
  • Enhanced operational flexibility, enabling rapid enrollment of new products and seamless expansion across retailers.
  • Multi-platform capability, with compatibility across mobile phone cameras, panoramic imaging, and robotic platforms.

By integrating computer vision, scalable infrastructure, and intuitive tools, OneSix built a flexible product identification platform that continues to power real-time shelf analytics and support evolving retail needs.

Ready to unlock the full potential of data and AI?

Book a free consultation to learn how OneSix can help drive meaningful business outcomes.

Contact Us

Boosting energy demand forecast accuracy by 24% for thousands of NYC buildings

  • Energy

Boosting energy demand forecast accuracy by 24% for thousands of NYC buildings

OneSix developed a deep learning-powered forecasting engine that improved demand forecast accuracy by 24% and automated long-range, hourly projections across 1,000+ buildings to support energy program participation.
Data Science
AI & Machine Learning
Forecasting & Prediction

Overview

Manual energy forecasting process limited accuracy and scalability

An energy management firm needed to forecast electricity demand across approximately 1,000 buildings in New York to support demand-response and energy-efficiency programs such as NYISO’s Special Case Response.

The existing process was slow, manual, and error-prone—relying on spreadsheets and rough estimations to determine seasonal commitments. The forecasts had to be both granular (hourly) and long-range (up to six months), while accounting for complex, interacting seasonal patterns across a wide variety of building types.

Our Solution

AI-powered forecasting engine enables smarter, scalable planning

OneSix developed a forecasting and simulation engine powered by deep learning. The solution included:

  • A hybrid model that combines classical state-space forecasting with a neural network architecture, allowing the system to capture nuanced seasonal patterns and their interactions.
  • Fourier-transformed inputs to effectively encode cyclical time-based features such as hour-of-day, day-of-week, and season-of-year.
  • A shared model architecture fine-tuned to each building, enabling scalability across diverse asset types—from subway stations and K–12 schools to wastewater treatment facilities.
  • Simulated future weather and load conditions to estimate global, correlated risk and support smarter demand-response planning.

The system was built using PyTorch and integrated with Torchcast to manage temporal data modeling and training workflows.

Results

Improved accuracy, automation, and program impact

  • 24% improvement in forecast accuracy during high-demand scenarios.
  • Automated, reliable seasonal projections across 1,000+ buildings, reducing manual effort and minimizing risk of human error.
  • Now serves as the foundation for setting program commitments, replacing the legacy manual process with a scalable, data-driven forecasting approach.

Ready to unlock the full potential of data and AI?

Book a free consultation to learn how OneSix can help drive meaningful business outcomes.

Contact Us

Boosting sales by 15% through marketing optimization for a spa franchise

  • Travel & Hospitality

Boosting sales by 15% through marketing optimization for a spa franchise

OneSix helped a luxury spa franchise optimize its marketing investments using data-driven analytics, leading to a 15% increase in prospect sales. By implementing a marketing data warehouse, marketing mix modeling (MMM), and automated budget optimization, the client gained real-time visibility into performance.
Data Science
AI & Machine Learning
AI-Driven Marketing
Power BI

Overview

Lack of visibility and ineffective marketing spend hindered growth

For a luxury spa franchise with hundreds of locations, ensuring marketing investments drive real value across national, regional, and franchise levels was a growing challenge. Without clear visibility into spend and performance, it was difficult to optimize marketing strategies and allocate budgets effectively. The client faced two key issues:

  • Limited Visibility: Minimal and delayed reporting of channel spend at national, regional, and local (franchise) levels made it difficult to assess marketing performance.
  • Inability to Improve Marketing ROI: Due to the lack of an empirical impact measurement strategy, the client struggled to make strategic investment decisions across marketing channels.

Our Solution

Data-driven marketing optimization to enhance budget efficiency

To solve these challenges, OneSix implemented a data-driven marketing optimization framework, leveraging advanced analytics and automation. Our approach was specifically designed to support a franchise model by providing both high-level and location-specific insights. Key aspects of our solution included:

  • Implementing a structured approach that accounts for national-, regional-, and franchise-specific effects on media efficiency and non-media influences.
  • Customizing adstocking and saturation functions, with parameters adaptable to specific groups.
  • Handling missing data and uneven time series across different franchise locations.
  • Incorporating multiple methods for time-based effects analysis.
  • Developing an optimization model tailored to the client’s specific needs, including group-specific constraints and budget allocations.

To bring this strategy to life, OneSix deployed a comprehensive suite of solutions:

  • Marketing Data Warehouse: Centralized all marketing and adjacent data into a unified data warehouse. Power BI was used to enable real-time, customizable reporting across all franchise levels.
  • Marketing Mix Modeling (MMM) Pipeline: Implemented an advanced MMM framework to evaluate the impact of various marketing channels on key performance indicators (KPIs), such as sales and customer acquisition. The MMM pipeline provided:
  • A structured method to quantify the contribution of each marketing channel.
  • Predictive insights to optimize future budget allocations.
  • Actionable recommendations to shift spending to high-performing channels.
  • Automated Marketing Optimization: Our proprietary MMM tool facilitated continuous, real-time budget optimization by integrating historical performance data, market conditions, and client-specific constraints.

Results

Improved marketing efficiency and measurable sales impact

By implementing these solutions, the client gained the ability to make data-driven marketing decisions with confidence. Key outcomes included:

  • Full automation of marketing budget allocation and spend/impact reporting, eliminating manual data reconciliation efforts.
  • 15% increase in prospect sales as measured in an initial experiment, directly attributed to optimized marketing budget allocations across channels.
  • Enhanced strategic decision-making through real-time visibility into national-, regional-, and franchise-level marketing performance.

Through OneSix’s expertise in data-driven marketing optimization, the luxury spa franchise gained unprecedented control over its marketing investments. With real-time insights and predictive modeling, the client can now continuously refine their marketing strategies, ensuring maximum return on investment across all franchise levels.

Ready to unlock the full potential of data and AI?

Book a free consultation to learn how OneSix can help drive meaningful business outcomes.

Contact Us

Crafting an AI-powered recommendation engine for a private equity service provider

  • Financial Services

Crafting an AI-powered recommendation engine for a private equity service provider

OneSix developed a recommendation engine for a private equity concierge service, using a large language model to match the best service providers from a large network, integrated into Salesforce with real-time chatbot functionality.
AI & Machine Learning
AI Agents & Chatbots
Snowflake
Fivetran

Overview

Streamlining service provider selection for PE concierge service

Our client connects private equity (PE) firms with service providers (SPs) for tasks such as diligence, value creation, and prep-for-sale, offers a “white-glove” concierge service. Their challenge was speeding up the process of selecting the best SPs from their large network to match new client needs, ensuring high-quality, timely recommendations for every new concierge.

Our Solution

AI-driven recommendation engine for efficient provider matching

OneSix built a recommendation engine using a domain-general large language model (LLM) to extract, distill, and embed unstructured data about past concierges and SP qualifications into a searchable vector database. This system allows agents to quickly search for and find the most relevant past concierges and SPs.

To enhance the relevance of the search results, a proprietary re-ranking model was included, ensuring that the recommendations are hyper-relevant and aligned with the client’s core sales metric. The engine was integrated into their Salesforce frontend via an API, and also exposed a natural language “chatbot” interface for real-time recommendations based on user input data.

Additionally, the system leverages existing data from Salesforce, Fivetran, and Snowflake, creating a specialized data-science schema to feed the recommendation engine. The Python app, connected to Snowflake via the Snowflake Python connector, powers the entire solution.

Results

Enhanced speed and quality in service provider selection

The recommendation engine is now used for all incoming concierge requests. Within Salesforce, agents receive a top-10 list of recommended SPs for each new concierge, allowing them to quickly choose the best-fit providers.

Success is measured by the percentage of engaged SPs that originated from the system’s recommendations, typically ranging between 60-80% each week. The solution has significantly streamlined the company’s SP selection process, delivering fast, high-quality matches to clients.

Ready to unlock the full potential of data and AI?

Book a free consultation to learn how OneSix can help drive meaningful business outcomes.

Contact Us

Achieving a 31% revenue increase by optimizing ad pricing for Dictionary.com

  • Technology

Achieving a 31% revenue increase by optimizing ad pricing for Dictionary.com

OneSix developed a machine learning platform for Dictionary.com to optimize ad pricing across segments, achieving a 31% revenue increase in one segment through dynamic, data-driven strategies worldwide.
AI & Machine Learning
AI-Driven Marketing

Overview

Optimizing ad pricing at scale for global reach

Dictionary.com, the first and largest digitally-native English language dictionary, serves tens of millions of users worldwide every month. With users accessing millions of definitions, synonyms, audio pronunciations, translations, and spelling help, Dictionary.com generates an immense amount of data daily. To optimize ad pricing at this scale, they needed a sophisticated solution that could leverage impression- and bid-level data, while being adaptive to the fast-evolving online advertising landscape.

Our Solution

Building a machine learning platform for ad floor optimization

OneSix partnered with Dictionary.com to create a powerful ad floor optimization platform powered by Apache Spark. This platform not only supported day-to-day production algorithms but also provided Dictionary.com’s in-house data science team the flexibility to prototype new algorithms and iterate on optimization strategies. 

Additionally, we developed a custom dashboarding tool to visualize key metrics and trends for each segment, equipping ad-yield managers with accurate market snapshots and optimal pricing recommendations.

Results

Significant revenue increase through optimized ad strategies

The implementation of the new ad floor optimization strategy led to a significant impact. In one experiment, Dictionary.com experienced a 31% increase in revenue in a targeted segment, demonstrating the effectiveness of the new optimization platform over previous strategies. This success has set a strong foundation for ongoing improvements in ad revenue and pricing strategies.

Ready to unlock the full potential of data and AI?

Book a free consultation to learn how OneSix can help drive meaningful business outcomes.

Contact Us

Maximizing casino player profitability with a one-to-one marketing engine

  • Travel & Hospitality

Maximizing casino player profitability with a one-to-one marketing engine

By implementing a one-to-one marketing engine with real-time personalization, OneSix helped a casino gaming provider enhance player experience and boost profitability through tailored offers.
AI & Machine Learning
AI-Driven Marketing
Snowflake

Overview

Revolutionizing loyalty marketing in casino gaming

Casino gaming is a high-energy industry that continually seeks to use state-of-the-art technology to improve the player experience. However, most loyalty marketing programs in the industry still follow traditional, tier-based direct marketing approaches. Using this model, casino patrons are evaluated based on monthly spending data, then categorized into low- to high-value tiers. Promotions like free play, restaurant discounts, and hotel perks are allocated by tier, with players receiving updates via direct mail or email.

This legacy system has significant drawbacks. Promotions are distributed only once a month, resulting in outdated information by the time offers reach players. Additionally, the process is labor-intensive and static, failing to respond to real-time changes in player behavior. Since players are grouped into broad value categories, the traditional approach also lacks personalization, preventing casinos from crafting customized offers that reflect individual preferences and engagement patterns.

In response to these limitations, our client, a leading casino gaming provider, partnered with OneSix to develop a solution capable of engaging players individually. The goal was to build a dynamic marketing engine that would automatically learn from players’ behaviors both online and in-casino, creating a personalized, real-time experience for each player.

Our Solution

Building a one-to-one marketing engine for personalized engagement

OneSix designed and implemented a one-to-one marketing engine powered by a distributed reinforcement learning platform, tailored specifically for the gaming industry’s needs. Recognizing that each player’s engagement is driven by unique behaviors, we developed a platform capable of continuously learning and adapting to individual player activity. This multi-channel “next best action” engine integrates data from multiple sources to generate a comprehensive, real-time view of each player.

The system leverages this data to make intelligent, individualized decisions, including when and how to communicate with each player. The engine streams out optimal actions that maximize engagement, offering personalized incentives and communication across various channels, such as email, direct mail, online platforms, in-app messages, and SMS. This approach allows the casino to engage each player based on their current behavior, creating a highly responsive, individualized experience that feels more relevant and timely than traditional loyalty programs.

In addition to building this powerful engagement engine, OneSix ensured that the platform would continue learning over time. Our solution includes a feedback loop that adjusts strategies based on player response, optimizing interactions to align with evolving preferences. This adaptive approach allows the casino to nurture player relationships effectively, combining the best of real-time analytics with advanced AI-driven marketing capabilities.

Results

Enhanced player experience and increased profitability

The deployment of this one-to-one marketing engine has transformed the client’s approach to player engagement, providing a more immediate and personalized experience for casino patrons. Players now receive offers tailored to their individual habits and preferences, and these offers are refreshed in near-real-time as new player data is collected.

Experimental testing of the platform has demonstrated substantial improvements in player profitability, as well as enhanced engagement and loyalty among both new players and those migrated from traditional loyalty programs. By responding to shifts in player activity and delivering customized offers across multiple channels, the casino has seen a marked increase in player satisfaction and profitability.

$450M

Annual player reinvestment

10%

Increase in player visits

6%

Increase in player profitability

Ready to unlock the full potential of data and AI?

Book a free consultation to learn how OneSix can help drive meaningful business outcomes.

Contact Us

Building the transport vehicle of tomorrow for a top 5 automotive company

  • Manufacturing

Building the transport vehicle of tomorrow for a top 5 automotive company

OneSix developed an AI-powered platform for a leading automotive company, enabling real-time parcel tracking and smart shelving to enhance delivery efficiency and streamline driver workflows.
AI & Machine Learning
Computer Vision

Overview

Enhancing delivery vehicle operations with in-vehicle automation

A top-5 global automotive company aimed to revolutionize commercial transportation by developing next-generation delivery vehicles that leverage AI for operational efficiency. Their vision focused on enhancing drivers’ workflows through automation—streamlining tasks without replacing drivers—to reduce time spent locating parcels and to optimize overall delivery processes. They needed a sophisticated, embedded AI solution capable of accurately identifying and tracking parcels within the vehicle in real-time.

Our Solution

Developing a platform for real-time parcel tracking and smart shelving

OneSix partnered with the automotive company to design an intelligent in-vehicle system. We deployed multiple sensors and cameras to detect and track parcels, along with proprietary algorithms for real-time object recognition and location tracking. Our platform integrated with in-vehicle hardware, enabling accurate detection, tracking, and management of parcels directly on the vehicle.

Additionally, we introduced Smart Shelves, LED-equipped shelves that guide couriers to the correct packages at the right delivery points, further reducing time spent searching within the cargo area. The platform was publicly demonstrated at a major international auto show in 2018, showcasing these key AI-powered features:

  • Automatic Parcel Scanning: The system identifies and decodes parcel barcodes as couriers enter the vehicle.
  • Comprehensive Parcel Tracking: Cameras and sensors detect and track each parcel’s position within the vehicle, providing a full view of the cargo for couriers and fleet managers.
  • Guided Package Retrieval: Smart Shelves direct the courier to the correct package via LED indicators, improving speed and accuracy during deliveries.
Multiple in-vehicle sensors and cameras are utilized to detect and track the positions and identities of parcels throughout the vehicle.
Smart shelves utilize LEDs to direct the courier to the correct package at the correct delivery location.

Results

Intelligent in-vehicle automation for enhanced delivery efficiency

The deployment of this AI-driven system provided the automotive company with an innovative, efficient approach to delivery management, transforming vehicle cargo spaces into smart, automated environments. The intelligent tracking and guidance solutions reduced operational delays, enhanced driver productivity, and increased overall delivery efficiency. This collaboration laid the groundwork for future advancements in commercial transportation automation.

Ready to unlock the full potential of data and AI?

Book a free consultation to learn how OneSix can help drive meaningful business outcomes.

Contact Us

Automating food inspection using deep learning for Sunsweet Growers

  • Manufacturing

Automating food inspection using deep learning for Sunsweet Growers

OneSix developed an AI-powered computer vision system for Sunsweet Growers, automating prune inspection with real-time defect detection while preserving high product quality standards.
Data Science
AI & Machine Learning
Computer Vision

Overview

Automating the prune inspection process while maintaining quality

Sunsweet Growers, the world’s largest prune distributor, aimed to automate its century-old manual inspection process to ensure product quality at scale. The new solution needed to match the reliability of the traditional process and operate as an edge device in areas with limited connectivity.

Our client’s goal was to build a single integrated provider marketing strategy powered by artificial intelligence. To do so, we had to predict not only how likely individual providers are likely to engage, but also how to intervene to change their probability of engagement. Additionally, as one of the largest pharmaceutical companies in the world, the data volume meant our solution had to be robust and architected to operate at scale.

Our Solution

Building an computer vision system for real-time defect detection

OneSix developed a computer vision solution using deep learning, deployed on portable edge devices to inspect prunes on-site. The solution comprised three key components: a hardware device capturing images from multiple angles, a cloud-based computer vision pipeline analyzing images for defects using custom-trained models, and a data warehouse for storing and visualizing inspection data. The system included a ‘human-in-the-loop’ component, allowing annotators to provide feedback on defect analysis to continuously improve model accuracy.

Results

Reliable, automated inspection ensuring quality and scalability

Since deployment, the system processes millions of prunes each season, delivering high-quality products with real-time defect detection. Sunsweet Growers’ team relies on the integrated monitoring and reporting dashboard throughout each production season, benefiting from an efficient, scalable inspection process that preserves product quality.

“OneSix designed, built and deployed a solution that integrated computer vision models with a monitoring/reporting dashboard that our team relies on throughout each production season. Since its initial deployment, as new challenges and opportunities have arisen, OneSix remains a valued collaborative partner to Sunsweet.”

Harold Upton, CTO

Ready to unlock the full potential of data and AI?

Book a free consultation to learn how OneSix can help drive meaningful business outcomes.

Contact Us