Innovative Integration Yields Unprecedented 92.5% Accuracy in Text-to-SQL Tasks

AtScale, a pioneering leader in data management and analytics, announces a significant breakthrough in Natural Language Processing (NLP). By integrating AtScale’s Semantic Layer and Query Engine with large language models (LLMs), AtScale has set a new standard in Text-to-SQL accuracy, achieving an impressive 92.5% across all combinations of question and schema complexities.

Also Read: AiThority Interview with Seema Verma, EVP and GM, Oracle Health and Life Sciences

“By feeding the LLM with relevant business context, we can achieve a level of accuracy previously unattainable, making Text-to-SQL solutions trusted in everyday business use.”

As enterprises generate and store increasing volumes of data, the demand for quick, accurate data analysis has never been higher, outpacing traditional methods reliant on human analysts. AtScale’s integration of Generative AI transforms natural language queries into precise SQL commands, dramatically improving efficiency and decision-making speed. While LLMs excel at generating human-like text, they often struggle with complex database schemas and business logic. AtScale’s Semantic Layer bridges this gap by providing LLMs with comprehensive business-side metadata, eliminating the need to create metrics from scratch or generate complex joins, and significantly enhancing result consistency and accuracy.

“Our integration of AtScale’s Semantic Layer and Query Engine with LLMs marks a significant milestone in NLP and data analytics,” said David Mariani, CTO and Co-Founder of AtScale. “By feeding the LLM with relevant business context, we can achieve a level of accuracy previously unattainable, making Text-to-SQL solutions trusted in everyday business use.”

Also Read: AiThority Interview with Kunal Purohit, President – Next Gen Services, Tech Mahindra

In rigorous testing, AtScale’s integrated solution outperformed traditional methods by a wide margin. Across a diverse set of 40 business-related questions, the solution achieved a 92.5% accuracy rate, compared to just 20% for systems without the Semantic Layer. These results underscore the system’s capability to handle a wide range of query complexities with superior precision.

Key Benefits of AtScale’s Solution:

1. Enhanced Accuracy: Achieves 92.5% accuracy in translating natural language questions into SQL queries.
2. Simplified Query Generation: Removes the need for LLMs to generate joins or complex business logic, reducing errors and improving efficiency.
3. Business Context Integration: Provides LLMs with essential business metadata, ensuring consistent and accurate results.

AtScale is committed to continuously advancing its AI-driven solutions. The company plans to enhance the integration further by optimizing prompt engineering and expanding training datasets, aiming to tackle even more complex queries with greater precision and efficiency. By doing so, AtScale seeks to empower businesses with increasingly robust and reliable data analysis tools.

Also Read: AiThority Interview with Yair Amsterdam, CEO of Verbit 

[To share your insights with us as part of editorial or sponsored content, please write to psen@itechseries.com]

The post AtScale Unveils Breakthrough in NLP with Semantic Layer and GenAI appeared first on AiThority.

TrusTrace, a global SaaS company with a market-leading platform for product traceability and compliance, has announced the completion of a (U.S.) $24 million growth investment led by Circularity Capital, a specialist investor in businesses that enable the circular economy, with participation from existing investors Industrifonden and Fairpoint Capital.

Recommended AI News: Glance Guided CX Now Available on Genesys AppFoundry

According to Shameek Ghosh, CEO and Co-Founder of TrusTrace, the new investment will enable the company to further accelerate its global expansion ambitions by strengthening its presence in key markets, deepening product innovation and expanding collaborations – helping to create a global network where all value chains are traceable, circular, and fair.

Ghosh commented: “A growing number of fashion and textile brands are adopting supply chain traceability to support their sustainability goals and ensure competitiveness in the face of mounting regulatory and consumer pressure. The completion of this growth investment is further evidence that businesses see traceability as critical to achieving their sustainability goals. Backed by new funding, TrusTrace will further cement its position as the fashion industry’s trusted partner for identifying and managing supply chain risk, ensuring compliance and driving sustainability across value chains.”

Traceability has accelerated in importance and momentum as a key enabler of sustainable transformation, as evidenced by TrusTrace’s five-fold growth in subscription revenue in the 27 months since the previous growth round by Fairpoint Capital and Industrifonden in 2021, preceded by seed funding from Backing Minds in 2019.

The company is widely considered the preferred supply chain partner for global fashion brands seeking to drive sustainable change, manage ESG risks and ensure compliance across their highly complex supply chains. Notable TrusTrace customers include adidas, Brooks Running, Tapestry, Asics and many more of the world’s largest apparel, footwear and l***** brands. TrusTrace also plans to offer its services to regional and mid-size brands in 2024.

Recommended AI News: IBM Debuts New Quantum Processor, IBM Quantum System Two, Advances Quantum Utility Era

Ghosh added: “We are delighted to be partnering with Circularity Capital for the next phase of our growth, the combination of their specialist expertise in the circular economy and powerful international network makes them a strong value-added investor for us.”

Anders Brejner, Investment Director at Circularity Capital, commented: “We see a growing number of global fashion brands looking to transition away from today’s linear ‘take-make-dispose’ model of production and consumption to one that is more sustainable and equitable. We believe this is only possible at scale with the right digital backbone to provide transparency and traceability across complex global supply chains. TrusTrace is a clear leader in this field, with an excellent team, solution and blue-chip client base – and a great fit with our strategy to back global leaders enabling the circular economy. We are excited to be supporting TrusTrace as it continues to expand worldwide.”

With more than a billion products now tracked through the platform, TrusTrace has established itself as a business-critical solution for supply chain traceability. The platform empowers brands with verified data in real-time, as materials and finished goods move through the supply chain. It also integrates seamlessly with retailer, manufacturer and supplier systems, as well as other third-parties, such as certification agencies, lifecycle datasets and other sustainability solution providers.

Founded in 2016, TrusTrace offers a market-leading platform for supply chain traceability and compliance, enabling brands and suppliers around the world to standardise how supply chain and material traceability data is captured, digitised and shared. Through providing access to validated supply chain data, TrusTrace empowers brands to identify, understand and improve the impact of their supply chain. The data can be used for risk management, compliance, product c***** and footprint calculations, offering the ability to share data confidently and easily about product origin, impact, and much more.

TrusTrace is leading global-scale traceability programs for many of the world’s largest brands. The company is headquartered in Stockholm, Sweden, with additional offices in India, France and the US.

Recommended AI News: Mission Cloud and MagellanTV Unveil Magellan Voice Works: Disrupting Global Content Delivery

[To share your insights with us, please write to sghosh@martechseries.com]

The post TrusTrace Completes (U.S.) $24 Million Growth Investment Led by Circularity Capital to Drive Global Expansion appeared first on AiThority.

• Comprehensive platform for collaborative sensor data capture, labeling, analysis, and modeling

• Powerful built-in visualizations, analysis packages and Python plugins unlock sensor data insights

• SensiML now accepting user registrations for limited invitation preview release

SensiML Corporation, a leader in AI software for IoT and a subsidiary of QuickLogic  announced the launch of Data Studio, a ground-breaking platform designed to redefine the landscape of sensor data management. With a focus on practicality and efficiency, Data Studio empowers engineers and data scientists by offering an integrated solution that addresses the most time-consuming tasks in AI engineering projects – creating high-quality datasets for evaluating and developing ML models.

Recommended AI News: Riding on the Generative AI Hype, CDP Needs a New Definition in 2024

According to Cognilytica, a well-respected AI / ML consulting firm, approximately 80% of the total time for machine learning (ML) projects is allocated to data preparation.  These tasks include data identification, aggregation, cleansing, labeling, and augmentation – all of which are supported in SensiML’s collaborative development environment.

SensiML Data Studio significantly improves productivity and simplifies dataset management for anyone working on sensor data ML projects. With real-time connectivity, intuitive visualization tools, sensor data video synchronization, and robust support for large-scale collaborative projects, it offers a seamless experience for developers on edge devices, gateways, PCs, and cloud platforms.

A comprehensive overview of all the features of Data Studio can be found on the SensiML website. The primary features are highlighted below:

• Effortless Data Capture and Import – Capture live sensor data, analyze it instantly, and label any data for seamless insights.
• Collaboratively Label Sensor Data – Employ flexible labeling methodologies for sensor data, including manual, AI-assisted, and custom – and sync video for effortless complex labeling. Store and analyze data locally on your computer or remotely.
• Data Analysis and Model Evaluation – Visually compare ML models, filter, transform, and fuse sensor data – all with built-in tools and your own Python expertise.
• Label and Data Versioning – Keep track of your labels and model results with versioned labels. Easily export your project to an open format.

“SensiML Data Studio makes sensor data management and analysis more accessible and efficient, empowering developers to build better, more impactful applications using sensor data across a wide range of industries,” said Chris Knorowski, CTO of SensiML.

Recommended AI News: Caresyntax Announces Strategic Collaboration With AAICO to Expand AI-Based Solutions in Healthcare

SensiML Data Studio is poised to transform sensor data analysis, offering a valuable resource for researchers, engineers, and data scientists across diverse sectors from agriculture and consumer wearables to medical devices, smart buildings, and factory maintenance.

Recommended AI News: FPT Software Joins Global Tech Giants in the AI Alliance as Founding Member

[To share your insights with us, please write to sghosh@martechseries.com]

The post SensiML Unveils Data Studio – Next-Generation Sensor Data Management for AI / ML appeared first on AiThority.

 WiMi Hologram Cloud a leading global Hologram Augmented Reality (“AR”) Technology provider announced that the deep convolutional neural network(DCNN) was used as the core algorithm for image recognition, and an augmented reality system that can recognize and track objects in dynamic scenes in real-time was designed so as to realize the recognition and localization of objects in augmented reality scenes. The DCNN has strong feature extraction and classification ability, which can extract useful feature information from complex images and use it for object recognition and tracking, and large-scale dynamic image datasets are used to train the DCNN in order to improve the recognition accuracy of the network.

Recommended : Top AI Pain Points that Challenge UK-based Marketers in 2023

DCNN is a special neural network structure mainly used for image recognition and computer vision tasks. It is composed of multiple convolutional, pooling and fully connected layers, each with a certain number of neurons. The core of DCNN is to achieve image classification and recognition by learning image features. The convolutional layer of a DCNN is its most important component, which extracts the features of an image by using a convolutional kernel that performs convolutional operations on the input image. The convolution kernel is used to obtain the output feature map by sliding over the input image and multiplying it element by element with the image and then summing the results. By stacking multiple convolutional layers, the DCNN can learn different levels of features, from low level to high level, and gradually extract more abstract features. The pooling layer is designed to reduce the size of the feature map and the number of parameters while retaining the most important feature information. Commonly used pooling operations are maximum pooling and average pooling, which take the maximum value or average value of local regions in the feature map as output, respectively. Through the pooling layer operations, the size of the feature map can be reduced, and the translation invariance and noise immunity of the features can be improved. The fully connected layer is the last layer of the DCNN, which spreads the outputs of the convolutional and pooling layers into one-dimensional vectors and classifies them by the neurons in the fully connected layer. Each neuron of the fully connected layer is connected to all the neurons of the previous layer. The fully connected layer learns weights and biases to achieve linear combinations and nonlinear transformations of the input features to obtain the final classification result.

WiMi took DCNN as the base model for image recognition. By training on a large amount of well-labeled image data, the network is allowed to learn the feature representations of different objects and accurately locate and recognize these objects in the input image. In order to accommodate the processing of dynamic images, WiMi adapted the network appropriately for information transfer and tracking between successive frames. Then, the recognized objects are combined with augmented reality to achieve real-time augmented reality effects. By integrating virtual objects with real scenes, it provides users with richer information and interaction.

Recommended :  New Generative AI-powered Sales Assistant Gets Closer to Perfection

This DCNN-based augmented reality dynamic image recognition has great potential for applications in fields such as gaming, education, and healthcare, bringing users a more immersive augmented reality experience. For example, in game development, the technology can be used to realize the recognition of dynamic characters and objects in the game; in intelligent transportation systems, the technology can be used to identify vehicles and pedestrians in the traffic scene; in the industrial field, the technology can be used to identify the equipment and products on the production line and so on. By combining deep learning and augmented reality technology, DCNN-based augmented reality dynamic image recognition technology provides a more accurate and efficient dynamic image recognition method.

DCNN-based augmented reality dynamic image recognition technology has great potential for development in the future. In the future, WiMi will further improve its performance and application scope through research on model optimization, dataset expansion, and multi-modal integration, to provide better support for the applications in the field of augmented reality.

Recommended : Using Unapproved GenAI Tools at Your Workspace? Salesforce has 6 Safe Use Recommendations

[To share your insights with us, please write to sghosh@martechseries.com]

The post WiMi Announces Convolutional Neural Network-based Augmented Reality Image Recognition appeared first on AiThority.

Adroit DI announces the hiring of two experienced industry leaders to build on the company’s recent global expansion and increase the size of its commercial infrastructure.

Recommended AI News: Cyient to Acquire Portugal-Based Celfinet to Strengthen its Wireless Communications Offerings

“I am very pleased that Adroit DI will be giving their first ever public presentation and live software demonstration at our October 31st New Molecular Modalities Mega Webinar. The world will get to see the cool and useful scientific software Adroit DI is bringing to the Chemistry market!”

Kerry Robinson, Ph.D. has been appointed Director of Business Development for North America and Government Sales. Based in Georgia, Kerry will oversee commercial activities and pursue new business and customer acquisition across the US market as well as US government institutions.

Jeff Buchanan has been appointed Director of Business Development for Asia Pacific, Australasia and South America. Based in Connecticut, Jeff will drive revenue growth through new client acquisition and building a partner network across the Asia Pacific, Australian and South American regions.

John F. Conway, Chief Visioneer Officer at 20/15 Visioneers said, “I am very pleased that Adroit DI will be giving their first ever public presentation and live software demonstration at our October 31st New Molecular Modalities Mega Webinar. The world will get to see the cool and useful scientific software Adroit DI is bringing to the Chemistry market!”

Recommended AI News: Wovenware Develops Open-Source Plugin to Adyen Payments Gateway; Extends Reach of Kill Bill’s Payments and B****** Platform

Richard Lingard, Adroit DI CEO, said, “We now have deep commercial leadership with the addition of John DelliSanti as Chief Commercial Officer and these two accomplished sales executives. We are well-positioned to capitalize on major market opportunities globally. What better day for these industry treats to join our team than Halloween itself!?”

President of North America and Chief Commercial Officer John DelliSanti said, “I’m excited to welcome Kerry and Jeff to the Adroit DI team. Their combined expertise will be crucial in executing our strategic sales and expansion plans.”

Adroit DI is a USA and UK-based technology company focused on developing cloud-based platforms that transform how researchers organize and leverage scientific data. By securely centralizing vast chemical and biological datasets in an intuitive interface, our scalable solutions break down data silos to support multi-disciplinary collaboration. Whether clients need to wrangle millions of molecules or integrate disparate data sources, Adroit DI’s flexible and affordable solutions foster insight by empowering easy exploration of connections across research domains. Our team of industry experts and data scientists is dedicated to continuously innovating new capabilities that help scientists spend less time on manual data management and more time achieving their scientific goals.

Recommended AI News: Sapia.AI Launches Regional Data Hosting Capabilities

[To share your insights with us, please write to sghosh@martechseries.com]

The post Adroit DI Continues Global Expansion with Appointment of Experienced Industry Leaders appeared first on AiThority.

The latest ‘large language model’ artificial intelligence system, GPT-4, could aid chemistry researchers, but limitations reveal the need for improvements.

GPT-4, the latest version of the artificial intelligence system from OpenAI, the developers of Chat-GPT, demonstrates considerable usefulness in tackling chemistry challenges, but still has significant weaknesses. “It has a notable understanding of chemistry, suggesting it can predict and propose experimental results in ways akin to human thought processes,” says chemist Kan Hatakeyama-Sato, at the Tokyo Institute of Technology. Hatakeyama-Sato and his colleagues discuss their exploration of the potential of GPT-4 in chemical research in the journal Science and Technology of Advanced Materials: Methods.

Recommended: AiThority Interview with Rob Walker, President of Global Growth Markets at Cognizant

GPT-4, which stands for Generative Pre-trained Transformer 4, belongs to a category of artificial intelligence systems known as large language models. These can gather and analyse vast quantities of information in search of solutions to challenges set by users. One advance for GPT-4 is that it can use information in the form of images in addition to text.

Although the specific datasets used for training GPT-4 have not been disclosed by its developers, it has clearly learned a significant amount of detailed chemistry knowledge. To analyse its capabilities, the researchers set the system a series of chemical tasks focused on organic chemistry – the chemistry of carbon-based compounds. These covered basic chemical theory, the handling of molecular data, predicting the properties of chemicals, the outcome of chemical processes and proposing new chemical procedures.

The results of the investigation were varied, revealing both strengths and significant limitations. GPT-4 displayed a good understanding of general textbook-level knowledge in organic chemistry. It was weak, however, when set tasks dealing with specialized content or unique methods for making specific organic compounds. It displayed only partial efficiency in interpreting chemical structures and converting them into a standard notation. One interesting feat was its ability to make accurate predictions for the properties of compounds that it had not specifically been trained on. Overall, it was able to outperform some existing computational algorithms, but fell short against others.

Recommended: Artificial Intelligence and the Trust Deficit: A Call for Greater Transparency

“The results indicate that GPT-4 can tackle a wide range of tasks in chemical research, spanning from textbook-level knowledge to addressing untrained problems and optimizing multiple variables,” says Hatakeyama-Sato. “Inevitably, its performance relies heavily on the quality and quantity of its training data, and there is much room for improvement in its inference capabilities.”

The researchers emphasise that their work was only a preliminary investigation, and that future research should broaden the scope of the trials and dig deeper into the performance of GPT-4 in more diverse research scenarios.

They also hope to develop their own large language models specializing in chemistry and explore their integration with existing techniques.

“In the meantime, researchers should certainly consider applying GPT-4 to chemical challenges, possibly using hybrid methods that include existing specialized techniques,” Hatakeyama-Sato concludes.

Recommended: AI and Machine Learning Are Changing Business Forever

[To share your insights with us, please write to sghosh@martechseries.com]

The post GPT-4 Artificial Intelligence Shows Some Competence in Chemistry appeared first on AiThority.

Popular open source tool Phoenix continues to expand what is possible in LLM evaluation, troubleshooting, and observability

Arize Phoenix, a popular open-source library for visualizing datasets and troubleshooting large language model (LLM)-powered applications, rolled out several industry-first capabilities in its latest release.

The update comes at a crossroads for generative AI, as new LLMOps tools race to keep up with the latest capabilities of foundation models. Over half (53.3%) of machine learning teams are planning production deployments of LLMs in the next year, but many continue to cite issues like hallucinations and responsible deployment as barriers in moving LLM-powered systems into the real world.

AiThority Interview Insights : AiThority Interview with Babak Pahlavan, Founder and CEO of NinjaTech AI

While the rise of LlamaIndex and LangChain has enabled developers to accelerate the development of applications powered by LLMs, the abstractions created by these frameworks can also make them complicated to debug. Phoenix’s new support for LLM traces and spans means that AI engineers and developers can get visibility at a span-level and see exactly where an app breaks, with tools to analyze each step rather than just the end-result.

This capability is particularly useful for early app developers because it doesn’t require them to send data to a SaaS platform to perform LLM evaluation and troubleshooting — instead, the open-source solution provides a mechanism for pre-deployment LLM observability directly from their local machine. Phoenix supports all common spans and has a native integration into LlamaIndex and LangChain.

The new Phoenix LLM evals library is also designed for fast and accurate LLM-assisted evaluations, ultimately making the use of the evaluation LLM easy to implement. Applying data science rigor to the testing of model and template combinations, Phoenix offers proven LLM evals for common use cases and needs around retrieval (RAG) relevance, reducing hallucinations, question-and-answer on retrieved data, toxicity, code generation, summarization, and classification. The Phoenix LLM evals library is optimized to run evaluations quickly with support for the notebook, Python pipeline, and app frameworks such as LangChain and LlamaIndex.

Read More about Interview AiThority: AiThority Interview with Gijs van de Nieuwegiessen, VP of Automation at Khoros

“As LLM-powered applications increase in sophistication and new use cases emerge, deeper capabilities around LLM observability are needed to help debug and troubleshoot. We’re pleased to see this open-source solution from Arize, along with a one-click integration to LlamaIndex, and recommend any AI engineers or developers building with LlamaIndex check it out,” says Jerry Liu, CEO and Co-Founder of LlamaIndex. 

“Large language models are poised to transform industries and society, but when it comes to robust performance going from toy to production remains a challenge,” said Jason Lopatecki, CEO and Co-Founder of Arize AI. “These industry-first updates from Phoenix promise to provide better LLM evals and deeper troubleshooting to make complex LLM-powered systems ready and reliable in the real world.”

Latest AiThority Interview Insights : AiThority Interview with Keri Olson, VP at IBM IT Automation

 [To share your insights with us, please write to sghosh@martechseries.com] 

The post Arize Premieres Open Source LLM Evals Library and Support for Traces and Spans appeared first on AiThority.

Private AI, a leading provider of data privacy software solutions, and Replica Analytics Ltd., an Aetion company, the leading Synthetic Data Generation technology provider for the healthcare industry, are pleased to announce a new partnership. The need for a privacy-preserving solution in healthcare is urgent and this strategic partnership aims to provide a comprehensive solution for healthcare’s data privacy and security challenges.

AiThority: The 3 Building Blocks to Make AI Accessible

Replica Synthesis 3.0, Replica Analytics‘ pioneering software generates synthetic structured data, in the place of real data, making healthcare data safe to use in medical research and for other valuable insights. Private AI’s industry-leading technology accurately detects and removes personally identifiable information from structured, semi-structured, and unstructured data – all of which are prevalent in the healthcare industry.

“By joining Private AI’s unique technology with Replica Analytics’ solution, we are now able to tackle the challenge of unstructured text and offer a more comprehensive solution to our global clients,” said Dr. Khaled El Emam, Replica Analytics’ SVP and GM, who has been developing and deploying privacy enhancing technologies for two decades. “Our companies share a deep commitment to privacy and to using data for good. Working together, we will make richer datasets available, which is essential for health research and analytics, while continuing to protect privacy.”

Latest Insights: Why Only AI and Data Analytics Can Stop Financial Criminals

“We are thrilled to partner with Replica Analytics and expand our cutting-edge data privacy solutions further into the healthcare industry through Replica Analytics and, in turn, expose their synthetic structured data generation product to other verticals,” said Patricia Thaine, CEO, and Co-Founder of Private AI. “With Replica Analytics’ synthetic data generation solutions, we can help our clients to create safe and secure data sets for tasks in which maintaining accurate statistical distributions of personally identifiable information are key.”

This partnership will enable healthcare organizations to extract valuable insights from their multi-modal data while ensuring compliance with HIPAA regulations and maintaining the highest levels of privacy and data security. The two companies aim to make healthcare data available for research and development while preserving individual privacy rights.

Read More: How ChatGPT Will Transform Customer Service

[To share your insights with us, please write to sghosh@martechseries.com]

The post Private AI and Replica Analytics Announce Partnership to Tackle Data Privacy appeared first on AiThority.

Foursquare, the leading independent geospatial technology platform,announced its geospatial knowledge graph a novel way of organizing geospatial datasets using graph technologies and the H3 grid system to transform how businesses derive value from location data.

Seventy-three percent of data strategy leaders agree that leveraging location intelligence across an organization is critical to driving utmost business results. However, extracting meaningful findings from location intelligence is a challenging feat. The process of ingesting and managing geospatial datasets to derive insights is a complicated obstacle that requires specialized skill and expensive hardware. The Foursquare Graph eliminates common challenges in achieving such results by pre-joining various geospatial data assets through well-defined relationships and minimizing the time and resources necessary to extract invaluable location-based insights.

AiThority: The 3 Building Blocks to Make AI Accessible

The Foursquare Graph also introduces a time-aware dimension to all geospatial datasets, facilitating spatiotemporal analyses that would not have otherwise been possible without significant infrastructure investments.

“Data is an essential resource for every company today, but rarely is it maximized to its full potential,” said Gary Little, President and CEO of Foursquare. “A pioneering use of H3 and graph technologies, the Foursquare Graph will harmonize the company’s full product suite, allowing for unprecedented querying, visualization capabilities, and advanced analytics to solve complex technical challenges that enable customers to unlock key business insights with ease and speed. This innovation will empower businesses to realize more value in geospatial data insights than previously possible.”

Accelerating Time to Business Value
Because geospatial data sets are often siloed, a significant amount of resources, specialized skill sets and tools are needed to prepare, clean and transform geospatial data before businesses find value from it.

Foursquare’s geospatial knowledge graph lowers the barrier to entry for location intelligence and limits the time it takes to uncover crucial insights within geospatial data queries. By indexing Foursquare’s proprietary datasets to the H3 grid and connecting them with well-defined relationships, Foursquare and its customers can quickly and easily join disparate geospatial datasets to unlock powerful insights that support specific, unique business needs. These insights can then be used to inform strategic business decisions and to improve core customer experiences.

Unlocking Privacy-First Insights
An industry standard, understanding consumer behavior in the physical world typically requires analysis at an individual level, a process that carries complex privacy implications. Foursquare’s application of geospatial graph technology accounts for these nuances by working with trends in aggregate, further protecting consumer data and aligning with Foursquare’s mission to serve as a pioneer in privacy.

Latest Insights: Why Only AI and Data Analytics Can Stop Financial Criminals

With this geospatial knowledge graph, insights are delivered at an aggregated level anchored in spatial units, such as a point of interest (POI), rather than the movement of an individual. For example, if a team is looking at where shoppers go either before or after they visit a store within a mall, the insights will be aggregated around the stores rather than the shoppers. With this transformative technology, businesses can now derive the same strong insights, without the need to share individualized data. Grounding data in spatial units rather than singular movements is a key way in which Foursquare remains committed to privacy-first location intelligence amid a rapidly evolving privacy landscape.

Foursquare Graph creates a single source of truth for data by serving as the central foundation for all Foursquare’s capabilities. It will also enhance Foursquare’s places and movement data to ensure completeness, accuracy and quality.

Read More: How ChatGPT Will Transform Customer Service

[To share your insights with us, please write to sghosh@martechseries.com]

The post The Industry’s First Application of Graph Technology to Geospatial Data, Meet the Foursquare Graph appeared first on AiThority.

Behavox, the leading provider of AI-driven compliance solutions, is making its Benchmark Test Datasets available to the industry. The datasets, mapped to specific risks and regulations, are designed to simplify the evaluation process for compliance professionals, monitors, and auditors, while ensuring the effectiveness of their surveillance programs.

 Latest AiThority Interview Insights : AiThority Interview with Malcolm Koh, Director, CX Practice at Zendesk

“With Behavox releasing its Benchmark Datasets, planted content can now be done as simply as copy and paste.”

The Behavox Benchmark Datasets were created by over 200 compliance professionals and have been carefully reviewed. They incorporate enforcement cases and years of experience, offering a robust dataset for evaluating the performance of AI solutions and lexicon scenarios.

These datasets are accompanied by detailed instructions on how to perform outcomes analysis and calculate recall and precision metrics. The release follows the launch of Behavox LLM, the most powerful domain-specific and task-specific AI for compliance surveillance, delivering unprecedented accuracy of compliance alerts. Behavox LLM captures 84% of risk phrases in the Behavox Benchmark Datasets, compared to mid-teens for lexicon scenarios.

Alex Glasman, Chief Data Scientist at Behavox, said, “Sharing Benchmark Test Datasets is considered best practice in AI, and it is a crucial part of rolling out AI responsibly. By making our Benchmark Test Datasets available, we aim to encourage collaboration and transparency across the industry, as well as improve the overall effectiveness of compliance surveillance.”

Read More about AiThority Interview: AiThority Interview with Jon Zimmerman, Chief Executive Officer at Holon Solutions

Fahreen Kurji, Chief Customer Intelligence Officer at Behavox, added, “For years, the industry has been grappling with inconsistent evaluation methodologies for surveillance programs, with the main pain point being the creation of planted content. With Behavox releasing its Benchmark Datasets, planted content can now be done as simply as copy and paste.”

With this announcement, Behavox invites consulting firms, regulators, academia, financial institutions, and auditors to review, use, and contribute to the Behavox Benchmark test dataset.

To experience AI for Compliance live in action, join Behavox on April 6th in NYC at their AI Summit. See how and why we have outperformed ChatGPT and learn more about explainable and effective AI compliance solutions.

AiThority Interview Insights: AiThority Interview with Kyle Wong, Chief Strategy Officer at Emplifi

 [To share your insights with us, please write to sghosh@martechseries.com] 

The post Behavox Makes Its Benchmark Test Datasets Available to the Industry appeared first on AiThority.