Browsing: Business & Startups

  # Introduction  Whether they are well-established classifiers or state-of-the-art massive models like large language models (LLMs), building machine learning solutions often entails a risk: algorithms might silently adopt prejudices inherent in the historical training dataset they were trained on. But in a high-stakes scenario or one where data is sensitive, how can we audit whether a model is biased without compromising real-world information? This hands-on article guides you in training a simple classification model for “loan approval” on biased data. Based on this, we will use Mimesis, an open-source library that can help generate a perfectly balanced, counterfactual dataset. You’ll…

Claude Cowork shifts AI from chat-based assistance to task delegation. Instead of giving users instructions, it performs actions directly on the user’s computer, files, applications, and browser workflows. Combined with Playwright MCP, Claude Desktop can open pages, click buttons, fill forms, extract data, and debug interfaces in a far more structured way than screenshot-based automation. Playwright MCP provides structured browser control through accessibility snapshots, enabling reliable AI-driven web automation inside Claude Desktop and other MCP clients. In this article, we’ll build a similar browser automation setup, covering installation, architecture, workflows, capabilities, limitations, security considerations, and practical business use cases. What…

pandas remains the default choice for notebooks, exploratory analysis, visualization, and machine learning workflows. Polars focus on fast, memory-efficient DataFrame processing, while DuckDB brings a SQL-first approach for querying local files and embedded analytics. Each tool fits a different kind of local data workflow. In this article, we compare pandas, Polars, and DuckDB across performance, architecture, interoperability, and real-world use cases. Differences Between pandas, Polars, and DuckDB For the ones looking for a high level difference between the three libraries, the following table should work: Area pandas Polars DuckDB Main identity Python DataFrame library High-performance DataFrame engine Embedded analytical database…

Alibaba’s Qwen team has unveiled Qwen3.7-Max, a flagship model built for the agent era. Unlike conventional chatbot-focused LLMs, it is designed as a foundation for autonomous AI agents that can code, debug, use tools, manage workflows, and execute long-running enterprise tasks. Alibaba claims the model can operate autonomously for up to 35 hours without performance degradation while supporting over 1,000 consecutive tool calls. In this article, we explore Qwen3.7-Max’s architecture, benchmarks, APIs, agent workflows, and its place in the evolving LLM ecosystem. What is Qwen3.7-Max?  Qwen3.7-Max is the newest member added to Alibaba’s Qwen line-up of proprietary models. It is…

  # Introduction  In a recent article on Machine Learning Mastery, we built a tool-calling agent that reached outward, that is pulling weather, news, currency rates, and time from public APIs. That article covered the synthesis half of the pattern nicely, but it left the more interesting half on the table: an agent that reasons about its own environment, inspects its own machine, and offloads logic it doesn’t trust itself to perform. It could be argued that this is closer to truly “agentic.” This article picks up where that one left off. We will give Gemma 4 two new tools —…

  # Introduction  If you have ever heard someone say they do quant trading and imagined a spreadsheet plus guesswork, it is actually much more structured than that. Quant trading is about using data, statistics, and code to make rule-based trading decisions you can test. You take ideas like momentum, mean reversion, or pairs trading, turn them into clearly defined strategies, backtest them on historical data, and then layer in risk management, position sizing, and execution logic. The goal is to be systematic and consistent instead of emotional and reactive. In this article, we review 10 GitHub repositories that cover strategies,…

  # Introduction  Even as AI can now generate huge amounts of code, system design remains one of the few skills that cannot be easily replaced. Writing code is only one part of building real products. Designing scalable, reliable, and efficient systems still requires experience, trade-offs, stakeholder discussions, and strong engineering judgment. That is exactly why system design continues to matter so much in technical interviews. It is not just about knowing the right answer. It is about how you think, how you break down complexity, and how you justify your decisions. For many engineers, this is also one of the…

Google Search just went from being an encyclopedia to an assistant. That’s the crux of everything Google announced in its recent I/O conference for 2026. The buzzword is “AI agents”, which now enter Google Search, its coding platforms, and even get a whole new standalone app for themselves. The idea is to move from AI that answers to AI that actually does things for you. Meaning – next time you are looking for that pair of jeans you love or a shirt you want on the internet, you don’t have to sift through an endless list of websites. Just tell…

  # Introduction  Here is something that should shift how you think about AI model size: a 4-billion-parameter model released in early 2025 is now outscoring models that were 7x larger on standard reasoning benchmarks. Google’s Gemma 3 4B posts an 89.2% on GSM8K math reasoning. Microsoft’s Phi-4-mini at 3.8B hits 83.7% on ARC-C, the highest score in its entire size class. These numbers used to belong to 30B+ models. So the question “do I really need a 70B model for this?” deserves a second look. For the purposes of this article, “small” means under 7 billion parameters — models that…

  # Introduction  Most of you use SQL window functions, but you’re only scratching the surface — a ROW_NUMBER() here, a SUM() OVER() there. The window functions’ real potential is revealed when you apply them to harder problems. I will walk you through four patterns that show window functions at their most useful.    The examples are all real interview questions you can practice on StrataScratch.   # Running Totals  Calculating running totals is one of the most common business uses of window functions. The finance people absolutely love it! It is used to track cumulative monthly revenue, which then easily moves…