Stratmillin tutkimusagentin kirjoittamia tiivistelmiä ja keskeisiä ajatuksia kirjoista, tutkimuksista, artikkeleista ja koodista, joita tekoälyagenttimme lukevat. Jokaisella sivulla on linkki alkuperäislähteeseen.
3,481 dokumenttia
This review surveys momentum investing across equities, funds, commodities, bonds, currencies, and cryptocurrencies. It explains cross-sectional momentum, which buys past winners and sells losers, and time-series momentum, which takes positions based on each…
This document is a short summary of a report about constructing a fund-of-funds portfolio that can consistently outperform the median actively managed equity fund. It highlights the difficulty of selecting funds that remain above that benchmark across…
The document considers why a developer might share or commercialize a quantitative trading system instead of trading it privately. Its central explanation is that developers may struggle to follow their own rules: watching short-term price moves can trigger…
The document summarizes an analysis of the China Strategic Emerging Industries Index and its associated ETF. The index selects 100 listed companies from areas such as environmental technology, information technology, biotechnology, advanced manufacturing,…
This tutorial introduces Pandas as a toolkit for working with financial data, focusing on its Series and DataFrame structures. It demonstrates creating indexed data, inspecting rows, columns, values, and types, sorting, transposing, selecting columns and…
The document explains the expected input, initial state, and output shapes for PyTorch’s LSTM layer. With the default layout, inputs are arranged as sequence length, batch size, and feature count; the hidden and cell states also include layer and direction…
This report summary examines gold supply and demand, macroeconomic influences, and ways to combine fundamental signals with short-term trend trading. It argues that supply changes relatively little, while shifts in investment demand help explain price…
This summary of a brokerage research report discusses the research workflow for multi-factor equity selection. It highlights source-data issues such as delayed or unreliable financial disclosures, corporate restructurings that disrupt historical…
The document surveys ways to revise investment strategies, including changing asset allocations, rebalancing, diversifying across assets, adding quantitative signals, and strengthening risk controls. It mentions tools such as value-at-risk, risk budgeting,…
The document introduces Bollinger Bands as a technical indicator calculated from closing prices. It names a moving-average window, another window for the lower band, and a standard-deviation multiplier as inputs. Its pseudocode describes an upper band based…
The document explains quantile regression as an alternative to ordinary least squares for modeling stock returns. Because it estimates relationships at different points in the return distribution, it can reveal effects that an average-based model may hide,…
The report summary describes a study of Chinese equities covered by broker buy-rating reports. Cross-sectional regressions reportedly find a significant return premium for covered stocks after controlling for common stock-selection factors. The premium is…
The document outlines an equity factor research workflow: define a hypothesis from investment or behavioral theory, gather and clean data, calculate factor values, evaluate each factor, combine factors, and backtest and refine the result. It highlights…
This study examines whether stock-selection factors earn premiums from choosing stocks within industries, allocating across industries, or both. It tests 21 definitions spanning value, quality, momentum, low volatility, and size, using global…
The article evaluates a deep-learning stock-ranking model across broad-market and filtered Chinese equity universes. It uses rolling windows of three years for training and one year for evaluation, then compares portfolio sizes, rebalance intervals,…
This research outline proposes constructing an A-share stock portfolio that seeks exposure to alpha while limiting unstable style exposures. Its motivation is concern that alpha-hedging returns may track market style rotations and that strategies experienced…
The document introduces the Psychological Line, abbreviated PSY, as a price-based indicator. Its stated calculation counts the days in a chosen lookback period when the close exceeds the previous close, divides that count by the period length, and expresses…
This report summary describes a study of capital-structure and solvency factors. It says nine capital-structure measures were assessed using grouped portfolio returns, long-short rankings, information coefficients, and Fama–MacBeth analysis. Four ratios were…
The document compares machine-learning approaches to strategy development with more subjective manual parameter tuning. It recommends measuring overfitting by comparing performance on training and test data, using cross-validation where appropriate. For…
The article argues that individual traders are unlikely to beat quantitative funds at speed and disciplined execution. It challenges the idea that simply refusing to sell is a reliable defense, pointing to the difficulty of holding through sharp price moves…
This introductory article defines quantitative investing as using numerical models and systematic rules to guide investment decisions. It contrasts model-based methods with more discretionary approaches, then describes claimed benefits: disciplined…
This document introduces a study of stock-selection factors based on herding behavior among individual Chinese equities. Its brief abstract places the work in the context of widely used domestic multi-factor strategies and says that such strategies had…
This note defines the Momentum Index, abbreviated Mtm, as the current closing price minus the closing price a specified number of days earlier. The lookback interval is a parameter, so the resulting value depends on the chosen period. The measure expresses…
A brief troubleshooting note explains a model training error in a stock ranking workflow. The stated cause is that all input factor values were either zero or one. Since the ranking model needs variation in its inputs to distinguish and order securities, a…