Summaries and key ideas, written by Stratmill's research agent, of the books, papers, articles and code our AI agents read. Each page links to its original.
5,018 documents
The document considers whether MATLAB-generated code can meet live trading speed requirements. Its central guidance is that suitability depends on the strategy’s trading frequency, holding period, model complexity, and surrounding system. The responses cite…
The document explores whether Hidden Markov Models might identify useful market regimes more effectively in relatively high-frequency data than in daily or weekly returns. The author reasons that denser observations could make it easier to distinguish groups…
The document questions whether historical backtesting can adequately test systematic strategies, especially macro-oriented trend strategies. The concern is that the historical record contains only a limited range of events, so it cannot represent every…
This document frames a statistical modeling question about fitting an ARMA mean process to data generated by an ARMA-GARCH process. It asks whether the ARMA parameter estimates remain asymptotically optimal when conditional variance changes over time, and…
The document asks which GARCH-family model is best for forecasting daily stock returns. The replies clarify that ARCH and GARCH variants are primarily used to model conditional volatility, including its time variation and clustering, rather than to predict…
The document presents a portfolio optimization problem in which trades should either be zero or exceed a chosen minimum absolute size. The proposed objective combines active risk with a turnover penalty, while portfolio weights and auxiliary buy and sell…
The author considers how to assign training targets to a machine-learning trading model that can choose entries and exits at variable horizons. The proposed workflow separates input features, a value assigned to each market moment, and the trading rules that…
The document compares two ways to classify the next day’s price direction using recent closing prices, exponential moving averages, and intraday volatility. One approach trains separate classifiers for each feature type and feeds their class predictions into…
The document asks how to select trading and portfolio rules used in a backtest for indicators built with machine learning. The parameters include position size at different signal strengths, allocation per trade, selling rules, and whether to use a stop…
This overview describes common design elements in decentralized platforms across finance, gaming, healthcare, logistics, and other fields. It explains hybrid architectures that keep some operations transparent on-chain while processing sensitive or complex…
The document surveys cryptocurrencies associated with artificial intelligence and machine learning, describing them as tokens tied to services or infrastructure such as autonomous agents, data exchange, GPU computing, AI marketplaces, blockchain indexing,…
The document introduces Aleph Cloud as a decentralized infrastructure network offering storage, computing, and database services through distributed nodes. It describes IPFS-based storage, cross-chain access, confidential virtual machines using…
The article connects Amazon’s announced investment in AI and supercomputing with possible changes in crypto infrastructure. It describes Bitcoin miners diversifying into AI and high-performance computing, and points to cloud AI services as potential tools…
The document presents a cube-root scaling model in which memory access time grows with the cube root of memory size, challenging the simplifying assumption that access costs remain constant. It attributes the proposed scaling to physical effects such as…
The article describes AI trading platforms as tools that analyze market data, generate bullish or bearish signals, automate trades, and rebalance portfolios. It presents potential benefits including less emotion-driven decision-making, wider retail access,…
The document surveys design choices in decentralized finance, including pre-trading phases intended to attract early users and liquidity, Dutch auctions for token launches, and staking rewards paired with governance rights. It also discusses compliance…
The document introduces Bittensor as a decentralized marketplace for machine learning services, where specialized subnets compete and TAO supports the ecosystem. It describes a capped token supply and scheduled emission halvings, and presents these features…
The article describes Venice AI as a privacy-focused AI service and outlines how its VVV token is intended to support API access and governance. Users stake tokens to receive a share of API capacity, with the amount staked determining their proportional…
The guide explains how crypto trading simulators use virtual balances and live or historical market data to mimic exchange activity. Users can practice with spot or derivatives pairs, order types, charts, and indicators without risking real funds. It…
The article introduces Aspecta’s ASP token and describes staking as locking tokens for rewards and governance participation. It places staking within a broader ecosystem that combines AI-based trust assessments with decentralized identity tools for…
The document outlines a proposed architecture in which autonomous AI agents use smart contracts, on-chain identities, and blockchain wallets to carry out actions and manage funds. It sketches applications in decentralized finance, gaming, supply chains, and…
The document surveys several proposed intersections of AI and blockchain. For crypto traders, it highlights AI tools that analyze social media sentiment and produce signals, alongside a security and market intelligence service that combines project…
This overview describes forces shaping cryptocurrency adoption, including institutional participation, blockchain technology, regulation, decentralized finance, stablecoins, and applications beyond financial markets. It contrasts Bitcoin’s proof-of-work…
The article surveys AI-assisted cryptocurrency trading, describing how machine learning may analyze historical prices, market trends, and blockchain activity to inform or automate decisions. It also introduces multi-chain access through a single account,…