Papers, wiki, Option Blackboard, encyclopedia, and cards.
In this work, we introduce PEARL (Private Equity Accessibility Reimagined with Liquidity), an AI-powered framework designed to replicate and decode private equity funds using liquid, cost-effective assets. Relying on previous research methods such as Erik Stafford's single stock selection (Stafford) and Thomson Reuters - Refinitiv's sector approach (TR), our approach incorporates an additional asymmetry to capture th…
In this paper, we consider a generic interest rate market in the presence of roll-over risk, which generates spreads in spot/forward term rates. We do not require classical absence of arbitrage and rely instead on a minimal market viability assumption, which enables us to work in the context of the benchmark approach. In a Markovian setting, we extend the control theoretic approach of Gombani & Runggaldier (2013) and…
Systemic liquidity risk, defined by the IMF as "the risk of simultaneous liquidity difficulties at multiple financial institutions", is a key topic in macroprudential policy and financial stress analysis. Specialized models to simulate funding liquidity risk and contagion are available but they require not only banks' bilateral exposures data but also balance sheet data with sufficient granularity, which are hardly a…
Neural networks for stock price prediction(NNSPP) have been popular for decades. However, most of its study results remain in the research paper and cannot truly play a role in the securities market. One of the main reasons leading to this situation is that the prediction error(PE) based evaluation results have statistical flaws. Its prediction results cannot represent the most critical financial direction attributes…
On a daily investment decision in a security market, the price earnings (PE) ratio is one of the most widely applied methods being used as a firm valuation tool by investment experts. Unfortunately, recent academic developments in financial econometrics and machine learning rarely look at this tool. In practice, fundamental PE ratios are often estimated only by subjective expert opinions. The purpose of this research…
Market trade-routes can support infectious-disease transmission, impacting biological populations and even disrupting causal trade. Epidemiological models increasingly account for reductions in infectious contact, such as risk-aversion behaviour in response to pathogen outbreaks. However, market dynamics clearly differ from simple risk-aversion, as are driven by different motivation and conditioned by trade constrain…
Automated market makers (AMMs) are a cornerstone of decentralised finance (DeFi). Constant product markets with concentrated liquidity, such as UniswapV3, are now a well-established design. In these markets, liquidity providers (LPs) face a sequential decision problem: they must decide when to rebalance their positions and which price ranges to allocate capital to as market conditions evolve. We formulate dynamic liq…
Building event-conditioned market models requires separating macro-event labels from persistent microstructure state. We study this distinction in Binance BTCUSDT and ETHUSDT futures from 2023-2026, combining top-20 L2 order book data, trade-flow records, and macro-event windows. We define a supervised discrete L2 liquidity-state transition task, distinct from latent-regime detection and price-direction prediction, a…
Large language models (LLMs) have shown strong performance across diverse financial tasks, yet portfolio management (PM) remains poorly benchmarked. Existing benchmarks exhibit two gaps: they are often equity-only and ignore cross-asset correlations; they fail to evaluate the complete PM decision pipeline. We introduce PortBench, a benchmark spanning six heterogeneous asset classes from 2015 to 2025. PortBench compri…
Prediction markets are starting to look less like crowd polls and more like electronic markets. The central question is therefore no longer only whether these markets forecast well, but what happens when institutional liquidity enters: do spreads tighten, does price discovery improve, and do those gains actually reach the traders who are slowest to react when information arrives? This paper offers a research design f…
We introduce $\textbf{Slippage-at-Risk (SaR)}$, a quantitative framework for measuring liquidity risk in perpetual futures exchanges. Unlike backward-looking metrics such as Value-at-Risk computed on historical returns or realized deficit distributions, SaR provides a \emph{forward-looking} assessment of liquidation execution risk derived from current order book microstructure. The framework comprises three complemen…
Three traits of decentralized finance are studied. First, the market impact function is derived for optimal-growth liquidity providers. For a standard random walk, the classic square-root impact is recovered. An extension is then derived to fit general fractional Ornstein-Uhlenbeck processes. These findings break with the linearized liquidity models used in most decentralized exchanges. Second, a Constant Product Mar…
We establish a general matched filter principle for order flow normalization: optimal normalization must match the scaling behaviour of the signal-generating process. For capacity-constrained institutional investors, market capitalization normalization ($S^{MC}$) is the matched filter; for volume-targeting traders (e.g., VWAP/TWAP algorithms), trading value normalization ($S^{TV}$) is optimal. Monte Carlo simulations…
We propose ARBITER, a risk-neutral neural operator for learning joint SPX-VIX term structures under no-arbitrage constraints. ARBITER maps market states to an operator that outputs implied volatility and variance curves while enforcing static arbitrage (calendar, vertical, butterfly), Lipschitz bounds, and monotonicity. The model couples operator learning with constrained decoders and is trained with extragradient-st…
We study opportunistic optimal liquidation over fixed deadlines on BTC-USD limit-order books (LOB). We present RL-Exec, a PPO agent trained on historical replays augmented with endogenous transient impact (resilience), partial fills, maker/taker fees, and latency. The policy observes depth-20 LOB features plus microstructure indicators and acts under a sell-only inventory constraint to reach a residual target. Evalua…
Concentrated Liquidity Market Makers (CLMMs) represent a fundamental innovation in market microstructure, transforming liquidity provision from passive portfolio allocation to active risk management. This evolution creates significant challenges for performance evaluation and strategy optimization, particularly due to the absence of comprehensive historical liquidity data. We address these challenges through a novel …
In this study, MLP models with dynamic structure are applied to factor models for asset pricing tasks. Concretely, the MLP pyramid model structure was employed on firm characteristic-sorted portfolio factors for modelling the large-cap US stocks. It was further developed as a practical factor investing strategy based on the predictions. The main findings were evaluated from 2 angles: model predictive power and backte…
We study a multi-agent setting in which brokers transact with an informed trader. Through a sequential Stackelberg-type game, brokers manage trading costs and adverse selection with an informed trader. In particular, supplying liquidity to the informed traders allows the brokers to speculate based on the flow information. They simultaneously attempt to minimize inventory risk and trading costs with the lit market bas…
Adam is an adaptive first-order optimizer that keeps exponential moving averages of the gradient and its square, giving per-parameter step sizes.
An agent workflow is a structured loop that plans, calls tools or models, observes results, and repeats until a stop condition — a pipeline with memory, contracts, and failure handling rather than a single completion.
Backpropagation computes gradients of a scalar loss with respect to every weight by applying the chain rule backwards through the computational graph.
BPE grows a vocabulary by repeatedly merging the most frequent adjacent pairs, starting from characters or bytes, until a target vocab size is reached.
CLIP jointly trains an image encoder and a text encoder so matched image–caption pairs are close in a shared space, enabling zero-shot visual classification by text prompts.
DQN approximates Q(s, a) with a deep net, using experience replay and a frozen target network so the TD target does not chase itself every step.
Fine-tuning continues training a pretrained model on a narrower distribution so the same weights specialize — classification heads, instruction following, or a desk domain.
GPT is a decoder-only Transformer trained to predict the next token. Scale plus this objective produced in-context learning and the current foundation-model product line.
LoRA fine-tunes a frozen model by learning low-rank adapters on selected weight matrices, cutting trainable parameters and storage versus full fine-tunes.
MoE routes each token (or example) to a sparse subset of specialist feed-forward experts, raising parameter count without paying dense FLOPs on every token.
The perceptron is the original trainable linear classifier: a weighted sum plus a threshold. It is the atom of neural nets, and it cannot learn XOR without a hidden layer.
Policy gradient methods optimize a parameterized policy π_θ directly by ascending the gradient of expected return, rather than via an action-value table.
Positional encodings inject order into a permutation-invariant attention mixer so the model knows that token i is not token j.
Prompt injection is an attack that inserts instructions into retrieved or user-supplied text so the model obeys the attacker instead of the developer’s system policy.
An RNN applies the same transition to a sequence, threading a hidden state through time: h_t = f(h_{t−1}, x_t). Plain RNNs struggle to learn long dependencies.
Regularization is any constraint that trades train fit for expected live error: weight decay, dropout, early stopping, data augmentation, or a simpler hypothesis class.
Reinforcement learning trains a policy to maximize expected return by interacting with an environment: states, actions, rewards, and (usually) a discount factor.
RLHF fits a reward model to human (or AI) preference comparisons, then optimizes a language model against that reward, usually with a KL penalty back to a reference policy.
A tokenizer splits raw text into the discrete tokens a model actually sees — bytes, characters, or learned subwords — and defines the vocabulary the softmax is over.
Deposit insurance is a public guarantee on eligible deposits up to a cap — a run-stopper that creates moral hazard and a hard cap problem.
KBW Bank Index tracks the equity performance of major U.S. banks and provides insight into banking-sector health, credit transmission, and market confidence.
Regional Bank ETF performance helps track stress in smaller and mid-sized banks, especially around deposit stability, asset quality, and local credit conditions.
Too big to fail is the expectation that a firm’s collapse would force a public rescue — a subsidy in funding spreads and a policy problem.
Copper price is widely used as a proxy for industrial activity, manufacturing demand, and global growth expectations.
CDX HY Index tracks the cost of insuring a basket of North American high-yield corporate credit and serves as a sensitive gauge of credit risk appetite and stress.
A convertible is a bond plus an embedded call on the issuer’s stock — credit with equity convexity, or equity with a coupon, depending on the delta.
High Yield OAS measures the spread of high-yield corporate bonds over risk-free Treasuries after adjusting for embedded options, serving as a key gauge of speculative credit stress.
Interest coverage is EBIT (or EBITDA) divided by interest expense — how many times operating profit can pay the coupon bill.
LGD is 1 minus recovery — the fraction of exposure lost when default happens.
Bitcoin Difficulty Adjustment — Periodic retarget of mining difficulty to stabilize block times.
A blockchain is an append-only replicated ledger with a consensus rule — a database with an incentive system, not a price target.
Crypto Perpetual Funding Rate — Periodic payment between longs and shorts that anchors perp to spot.
A stablecoin is a token that targets a peg, usually $1 — a money-market claim or an algorithmic hope, depending on the reserves.
Size each new futures position so that 1 ATR move equals a fixed fraction of equity — the Turtle risk unit, still the cleanest per-trade language.
A CTA is a manager — often CFTC/NFA registered — that runs client money in futures and options on futures, long and short, across rates, FX, equities, and commodities.
A CTA that tries to pick turns — anticipatory shorts of highs and buys of lows — the opposite personality of a breakout shop.
Code-linked scanner pattern that maps front-vol stress, ATM IV, and dealer gamma context into Blackboard + Options Lab actions.
Vol-structure note for classifying rich vs cheap ATM IV and surface dispersion before choosing credit or debit templates.
Scanner code fragment for put/call ratio and open-interest activity on the ATM chain window.
Educational IV × Greeks × surface sandbox already mounted on the Blackboard — synthetic regimes for pedagogy beside the live scanner.
The 2s10s Treasury curve measures the spread between 10-year and 2-year Treasury yields and is a key indicator of growth expectations, policy path, and term structure dynamics.
Adam is an adaptive first-order optimizer that keeps exponential moving averages of the gradient and its square, giving per-parameter step sizes.
Adverse selection is the expected loss a liquidity provider takes when the other side is informed — the Glosten–Milgrom reason spreads exist even with no inventory.
An agent workflow is a structured loop that plans, calls tools or models, observes results, and repeats until a stop condition — a pipeline with memory, contracts, and failure handling rather than a single completion.
Alpha is return not explained by the risk factors you chose — a residual, not a personality.
Alpha Decay — Speed at which a signal loses predictive power as capital competes for it.
Animal spirits is Keynes’s name for the non-model confidence that makes people invest or refuse to — the residual when rates and cash flows are not enough to explain the tape.
Argentina’s 2001–02 collapse ended the convertibility 1:1 peg with default, corralito, and a violent real devaluation — a political-economy crisis of an overvalued peg.
The 1997–98 Asian crisis was a sequence of peg breaks, bank runs, and sudden stops starting in Thailand — short-dollar corporate debt plus weak bank regulation meeting a reversal of carry.
An asset is a present economic resource controlled by an entity from which future cash or service is expected — the left-hand side of the balance sheet.
Size each new futures position so that 1 ATR move equals a fixed fraction of equity — the Turtle risk unit, still the cleanest per-trade language.
Backpropagation computes gradients of a scalar loss with respect to every weight by applying the chain rule backwards through the computational graph.
Backtest Overfitting — False discovery from mining historical patterns that do not persist out-of-sample.
The balance sheet is the stock of assets, liabilities, and equity at a date — what the firm owns and owes, not the period’s flow.
Barings Bank was wiped out in 1995 by Nick Leeson’s hidden Nikkei futures losses in Singapore — a rogue-trader plus failed control story, not a macro crisis.
A bear market is a sustained decline in a broad index — the folk threshold is −20% from a peak, which is a headline, not a model.
A bear steepener is a curve move where long yields rise more than front yields (or fronts fall less) as the market prices more term premium, more deficit, or less faith in long-run restraint — and duration loses.
Behind the curve means policy (or a book) is too easy or too slow relative to incoming inflation, growth, or a Taylor-type benchmark — the market is already pricing a catch-up.
Beta is the regression slope of an asset’s return on a factor (usually the market) — a hedge ratio, not a destiny.
The same BAB recipe on country indexes or international stocks — low-beta vs high-beta outside the US single-name tape.
Bitcoin Difficulty Adjustment — Periodic retarget of mining difficulty to stabilize block times.
Black-Scholes is the European option formula under lognormal spot, constant vol, and continuous hedging — a quoting convention more than a belief about the world.
A blockchain is an append-only replicated ledger with a consensus rule — a database with an incentive system, not a price target.
Brownian motion (Wiener process) is the continuous-time random walk with independent Gaussian increments — the backbone of Black–Scholes, Ito calculus, and most diffusion models.
A funding-stress monitor can warn before equity volatility reprices.
A liquidity premium monitor can separate default risk from liquidity-driven spread widening.
A reusable card for converting research papers into buildable strategy or monitoring objects.
A card for tracking cross-currency basis, repo dislocations, and balance-sheet stress as early warning signals.