Data & Analytics

DeepLOB-Deep-Convolutional-Neural-Networks-for-Limit-Order-Books is a Jupyter notebook project showcasing the application of deep convolutional neural networks to analyze limit order books. This tool is based on research published in IEEE Transactions on Signal Processing, providing a practical demonstration of the methodologies presented in the paper. It utilizes the publicly available FI-2010 dataset to illustrate how the model architecture is constructed and implemented. The project offers implementations in both TensorFlow (versions 1 and 2) and PyTorch, making it accessible to researchers and developers familiar with either framework. It serves as a valuable resource for understanding and replicating advanced deep learning techniques in financial market analysis.

Eyrene is an AI-powered digital merchandising platform designed to enhance on-shelf presence through advanced mobile image recognition technology. It accurately identifies products, price tags, promotions, and other in-store elements in real time, functioning offline and supporting both Android and iOS devices. The platform includes a KPI engine to calculate key industry metrics like share of shelf (SOS), on-shelf availability (OSA), and planogram compliance, providing instant actionable insights for field teams and detailed data for headquarters. A sophisticated web portal offers data visibility and control over field operations, while integrated BI dashboards (powered by Microsoft PowerBI Embedded) provide comprehensive data aggregation and visualization. Eyrene also offers rich integrations and APIs, a supervisor mobile app for real-time updates, and professional services for customization, ensuring a tailor-made solution for various retail needs.

FORMCEPT offers a continuous decision intelligence system, MecBot, designed to automatically infer business risks and opportunities from internal and external data in real-time. It guides business users and AI agents on necessary actions, featuring context-aware, explainable, and traceable AI that integrates with existing data stacks. MecBot helps businesses foresee downstream impacts, update decision logic continuously, and scale real-time intelligence with unlimited users and queries. Key modules include MecGPT for Gen AI assistance in data analysis, MecBrain for building data connections, and MecSense for pattern detection. The platform also supports various use cases like monitoring devices, informing sales decisions, and building data-driven solutions, with a 45-day go-live guarantee.

The NSFW Content Detection API is an AI-powered solution designed to automatically identify and flag not-safe-for-work content within images. This tool is crucial for platforms and applications that require robust content moderation to ensure user safety and maintain community guidelines. By providing a score from 0.0 to 1.0, the API quantifies the probability of inappropriate material being present, allowing for automated or semi-automated content review processes. This helps in efficiently scaling content moderation efforts, reducing manual workload, and ensuring a safer online environment for users.

Sage Marketer is an AI-powered platform designed to elevate marketing efforts through data-driven content generation. It integrates marketing data to enable personalized, AI-powered content creation across all channels, transforming data into high-impact, conversion-driving marketing content. The tool offers features like an AI Image Editor for stunning visuals, an AI Blog Post Editor for SEO-optimized articles, and an AI Newsletter Editor for compelling email content. It also helps capture and maintain a consistent brand voice, generates content ideas based on trending news and past performance, and is suitable for freelancers, marketing agencies, and in-house marketing teams.

Forestreet is an AI-powered platform designed to revolutionize supplier discovery and market intelligence for procurement and category managers. It allows users to search across millions of potential vendors globally in seconds, indexing and enriching data to create curated lists based on specific criteria. Unlike traditional methods, Forestreet's platform is not skewed by sponsored content or limited by recycled supplier lists, ensuring comprehensive market capture. It provides high-quality context and insights, enabling category managers to become multi-lingual experts with global perspective and local knowledge. The platform also offers features like market categorization, relevant news article access, high-quality analytics, and auto-generated reports, making it a force-multiplier for research time.

Tomorrow.io Weather API offers hyper-accurate weather data with over 80 layers and insights, enabling organizations to predict, automate, and solve complex weather challenges. Leveraging a first-of-its-kind commercial weather-sensing satellite constellation and AI-powered fusion of satellite and global data, it provides adaptive modeling for various industries. The platform offers solutions for enterprise, aviation, rail/transportation, pharmaceuticals/healthcare, insurance, government, and defense. It includes features like real-time weather, historical weather data, API map visualization, localized severe weather alerts, and air quality information, making it a comprehensive weather intelligence and resilience platform.

Excel Whisper is a privacy-first AI tool designed for analyzing Excel and CSV data using natural language. Users can upload their files and ask questions or give commands, and the tool will perform tasks like data cleaning, visualization, and calculations. A key differentiator is its commitment to privacy, as all data processing happens locally within the user's browser, meaning data never leaves the device. It supports multi-file analysis, quick visualization generation, and smart data cleaning, making complex spreadsheet tasks accessible without needing advanced Excel formula knowledge. The tool focuses on automating repetitive tasks and basic analysis, empowering users to derive insights efficiently while maintaining control over their sensitive information.

Emotion-recognition-neural-networks is an open-source project developed for emotion recognition using deep neural networks, specifically with TensorFlow. It employs convolutional neural networks (CNNs) for mood recognition, utilizing the FER-2013 Faces Database which contains 28,709 pictures across 7 emotional expressions. The project provides scripts for data transformation from CSV to NumPy, and supports training models using architectures like AlexNet. While the repository notes that the code might not be actively maintained or fully functional, it serves as a foundational academic project for those interested in exploring DNN-based emotion recognition.

ENACOM Group specializes in developing and regionalizing advanced computational methods for various engineering applications. The company's core expertise lies in areas such as multiobjective optimization, machine learning, and data mining. ENACOM is committed to fostering technological development within Brazil, actively supporting research initiatives, and facilitating the transfer of technology to practical applications. While specific features are not detailed on their website, their focus suggests a strong emphasis on scientific and statistical analysis, likely catering to technical professionals in engineering and research fields.

Tranquility AI offers TimePilot, an AI-powered platform designed to accelerate investigations for law enforcement, prosecution, military & intelligence, and government agencies. The tool analyzes various data sources, uncovers critical evidence, and builds detailed work products, significantly speeding up the path to justice. TimePilot automatically maps relationships across all evidence types, revealing hidden patterns that might otherwise be missed. It rapidly processes data, transforming scattered information into clear, automated discoveries, helping teams find answers in seconds. The platform is trusted by various departments across the country, with testimonials highlighting its ability to find crucial evidence in complex cases and organize decades of material for cold case investigations.

Strella is an AI-powered customer research platform designed to help product, design, and marketing teams gain customer insights 10x faster. It leverages AI to run in-depth, moderated interviews and provides real-time synthesis of responses, significantly reducing the time required for customer research. The platform can generate unbiased discussion guides, recruit participants from an 8M global panel, and analyze key themes across responses. Strella supports various research types including market research, usability testing, and concept testing, and offers features like AI-powered probing, instant highlight reels, and multi-language support across 46+ languages.

embetter is an open-source Python library designed to provide useful embeddings for scikit-learn pipelines, making it easy to quickly build proof of concepts for machine learning tasks. It offers scikit-learn compatible embeddings for both computer vision and text data, simplifying the integration of advanced embedding techniques into existing workflows. The library is particularly helpful for bulk labeling efforts and plays well with tools like scikit-partial for handling out-of-core datasets. It includes components for grabbing data from pandas DataFrames, various encoders for images (TimmEncoder, ColorHistogramEncoder) and text (SentenceEncoder, MatryoshkaEncoder), and multi-modal models like ClipEncoder. Additionally, it supports finetuning components and external embedding providers requiring API keys, such as Cohere and OpenAI.

moonbird AI specializes in expert-led, AI-powered tools designed to enhance and modernize Adobe Experience Cloud implementations. Their flagship products include Ivory, which reimagines tag management for Adobe Tags by allowing users to search, create, and edit rules using natural language, and perform bulk operations. Starling accelerates Web SDK upgrades from AppMeasurement, promising up to 90% faster timelines through AI-powered automation for requirements gathering, schema design, and technical conversion. Beyond products, moonbird AI offers consulting services for custom AI and analytics solutions, partnering with organizations to diagnose needs and design bespoke AI-powered strategies. Their solutions are built by practitioners with deep expertise in analytics and AI, ensuring practical and effective outcomes.

The PatchCamelyon (PCam) benchmark is a challenging image classification dataset designed for deep learning in medical imaging. It comprises 327,680 color images (96 x 96px) extracted from histopathologic scans of lymph node sections. Each image is annotated with a binary label indicating the presence of metastatic tissue, making it ideal for training and evaluating machine learning models for metastasis detection. PCam is larger than CIFAR10 but smaller than ImageNet, allowing models to be trained on a single GPU within a few hours. It serves as a valuable resource for fundamental machine learning research on topics such as active learning, model uncertainty, and explainability, particularly within the medical domain. The dataset is provided in gzipped HDF5 files and includes training, validation, and test sets with balanced positive and negative examples.

FinWise AI is designed to be an intelligent financial companion, offering users AI-powered assistance for their financial needs. While specific features are not detailed on the provided website content, the consistent branding across multiple pages (homepage, pricing, plans, features, FAQ, docs) suggests a comprehensive platform. The tool aims to provide smart solutions for managing finances, likely leveraging artificial intelligence to offer insights, recommendations, or automated tasks. It positions itself as a go-to resource for individuals or businesses seeking to enhance their financial understanding and decision-making through technology.

Food-Recipe-CNN is a deep learning project designed to recognize food images and suggest matching recipes. Utilizing deep convolutional neural networks (CNNs) with Keras, this system can classify food images into 230 distinct categories. The project leverages a large dataset of over 400,000 food images and 300,000 recipes from chefkoch.de. It employs transfer learning with pre-trained CNNs like InceptionV3 and VGG16, alongside feature extraction and dimensionality reduction techniques such as PCA. The goal is to provide a solution for automated recognition of photographed dishes and subsequent recipe retrieval, with a web application called DeepChef in development.

Xsolis offers AI-powered solutions and services designed to optimize healthcare operations for both providers and payers. Its flagship Dragonfly platform leverages real-time data-driven analytics and AI/ML insights to streamline medical necessity decisions, discharge planning, and payer-provider collaboration. Key functionalities include optimizing admission decisions, driving real-time precision for continued stay management, empowering proactive care coordination for discharge, and supporting medical necessity and reimbursement decisions to prevent denials. Xsolis aims to reduce administrative burden, enhance revenue integrity, and improve patient throughput by transforming fragmented clinical data into consistent, evidence-based decisions.

Open Researcher is a powerful AI-powered research tool designed to streamline the process of searching, analyzing, and understanding web content. It leverages Firecrawl's web scraping capabilities to gather accurate and up-to-date information, which is then processed by advanced AI reasoning, powered by Anthropic's Claude. Key features include an AI-powered search, a real-time thinking display that shows the AI's reasoning process, smart citations for automatic source tracking, and a split-view interface for side-by-side chat and search results. This tool is ideal for anyone needing to efficiently research and synthesize information from the web, providing a transparent and well-sourced analysis.

Fuji-Web is an intelligent AI agent designed to automate web-based tasks directly from your browser's sidepanel. It understands user intent, navigates websites autonomously, and executes tasks on your behalf, providing explanations for each action taken. This transparency allows users to maintain control while leveraging AI for efficiency. The tool is installed as a browser extension, requiring an OpenAI or Anthropic API key for functionality. It supports complex and cross-tab workflows, with future plans for integration with browser automation frameworks like Puppeteer and Playwright, as well as features for saving and sharing workflows. Fuji-Web is open-source, allowing users to build the extension from source.

BrandMov is an agent-first Meta ads intelligence tool designed to help marketers track competitor creative strategies and scale winning ads. It eliminates the need for manual checking by providing real-time alerts when competitors launch new creative. Users can browse Meta's public ad library visually, save ads to named swipe file collections with notes, and share workspaces with teams. BrandMov integrates with AI agents like Claude and Cursor via its MCP-native API, offering 39 tools for competitor watchlists, AI ad scoring, and full Meta campaign management. It also includes 8 growth tools such as an ad copy grader and hook generator, all with a one-time lifetime deal.

CityFALCON is an AI-driven platform designed for personalized financial and business due diligence, offering comprehensive news and intelligence across stocks, companies, asset classes, sectors, events, people, and over 300,000 topics. It caters to a wide audience, from retail investors and traders to enterprise clients like brokers, wealth managers, and institutional investors. The platform leverages Big Data and AI to provide features such as sentiment analysis, news summaries, relevance scores, ESG content, and real-time market insights. Users can access content via a web interface or through APIs, enabling integration into existing systems for enhanced decision-making and due diligence processes.

BuzzBoard is an AI platform designed for high-volume marketing service providers, including enterprise providers, agencies, platforms, publishers, and resellers, who serve small and medium-sized businesses (SMBs). It streamlines the entire marketing lifecycle, from selling and launching to managing multi-channel programs such as ads, social posts, emails, and SEO content. The platform features a suite of AI agents like Ignite for sales, Zylo for fulfillment, and Ember for retention and growth. BuzzBoard leverages deep SMB intelligence and coordinated AI systems to unify selling, fulfillment, and customer success, allowing providers to scale profitably and deliver consistent outcomes at volume. It is SOC 2 Type II compliant, ensuring enterprise-grade security for customer data.

GDN is an open-source implementation of the research paper "Graph Neural Network-Based Anomaly Detection in Multivariate Time Series" presented at AAAI 2021. This tool provides the necessary code to perform anomaly detection in multivariate time series data by leveraging graph neural networks. It is designed for researchers and developers working with time series analysis and anomaly detection, offering a practical framework for applying advanced graph-based methods. Users can prepare their datasets, configure parameters, and run the model on both CPU and GPU environments. The repository includes scripts for installation, training, and evaluation, making it a valuable resource for those looking to implement or experiment with this specific anomaly detection technique.