Papers, wiki, Option Blackboard, encyclopedia, and cards.
We present a new financial framework where two families of RL-based agents representing the Liquidity Providers and Liquidity Takers learn simultaneously to satisfy their objective. Thanks to a parametrized reward formulation and the use of Deep RL, each group learns a shared policy able to generalize and interpolate over a wide range of behaviors. This is a step towards a fully RL-based market simulator replicating …
Order flow is toxic when it adversely selects market makers, who may be unaware they are providing liquidity at a loss. We present a new procedure to estimate flow toxicity based on volume imbalance and trade intensity (the VPIN toxicity metric). VPIN is updated in volume time, making it applicable to the high-frequency world, and it does not require the intermediate estimation of non-observable parameters or the app…
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…
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…
Everlasting options, a relatively new class of perpetual financial derivatives, have emerged to tackle the challenges of rolling contracts and liquidity fragmentation in decentralized finance markets. This paper offers an in-depth analysis of markets for everlasting options, modeled using a dynamic proactive market maker. We examine the behavior of funding fees and transaction costs across varying liquidity condition…
Sunshine trading theory predicts that publicly disclosing trading intentions can reduce adverse selection and attract liquidity provision, lowering execution costs. Evidence is scarce, because explicit preannouncement of large orders is rare in traditional markets. We study Hyperliquid, a fully on-chain limit order book for cryptocurrency perpetual futures, where protocol-native TWAP orders disclose their terms from …
The alignment of Multi-Agent Systems (MAS) for autonomous software engineering is constrained by evaluator epistemic uncertainty. Current paradigms, such as Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF), frequently induce model sycophancy, while execution-based environments suffer from adversarial "Test Evasion" by unconstrained agents. In this paper, we introduce an objective alignment pa…
Large language models (LLMs) achieve strong performance across benchmarks--from knowledge quizzes and math reasoning to web-agent tasks--but these tests occur in static settings, lacking real dynamics and uncertainty. Consequently, they evaluate isolated reasoning or problem-solving rather than decision-making under uncertainty. To address this, we introduce LiveTradeBench, a live trading environment for evaluating L…
In the highly volatile and uncertain global financial markets, traditional quantitative trading models relying on statistical modeling or empirical rules often fail to adapt to dynamic market changes and black swan events due to rigid assumptions and limited generalization. To address these issues, this paper proposes QTMRL (Quantitative Trading Multi-Indicator Reinforcement Learning), an intelligent trading agent co…
In the rapidly evolving world of financial markets, understanding the dynamics of limit order book (LOB) is crucial for unraveling market microstructure and participant behavior. We introduce ClusterLOB as a method to cluster individual market events in a stream of market-by-order (MBO) data into different groups. To do so, each market event is augmented with six time-dependent features. By applying the K-means++ clu…
Deep reinforcement learning (DRL) has been envisioned to have a competitive edge in quantitative finance. However, there is a steep development curve for quantitative traders to obtain an agent that automatically positions to win in the market, namely \textit{to decide where to trade, at what price} and \textit{what quantity}, due to the error-prone programming and arduous debugging. In this paper, we present the fir…
As deep reinforcement learning (DRL) has been recognized as an effective approach in quantitative finance, getting hands-on experiences is attractive to beginners. However, to train a practical DRL trading agent that decides where to trade, at what price, and what quantity involves error-prone and arduous development and debugging. In this paper, we introduce a DRL library FinRL that facilitates beginners to expose t…
We consider trading against a hedge fund or large trader that must liquidate a large position in a risky asset if the market price of the asset crosses a certain threshold. Liquidation occurs in a disorderly manner and negatively impacts the market price of the asset. We consider the perspective of small investors whose trades do not induce market impact and who possess different levels of information about the liqui…
Traders are often faced with large block orders in markets with limited liquidity and varying volatility. Executing the entire order at once usually incurs a large trading cost because of this limited liquidity. In order to minimize this cost traders split up large orders over time. Varying volatility however implies that they now take on price risk, as the underlying assets' prices can move against the traders over …
Indonesia has established a regulated carbon market supported by national registry infrastructure and the IDXCarbon exchange. Carbon units can be issued, recorded, traded, and retired within this framework. IDXCarbon currently uses a private blockchain for its trading infrastructure. This creates an opportunity to examine how Indonesian carbon credits could also be represented and traded through public blockchain inf…
This paper studies a modular cash-overlay rule for allocating between a fixed growth-defensive risky sleeve R and interest-bearing cash C. The risky sleeve is a static 50/50 combination of equal-weight growth/technology and defensive income/value ETF baskets; the target is future R-C return, with the cash leg earning the contemporaneous cash rate. Two independent filters are tested. The slow-tail filter maps continuo…
Scaling generative inverse and forward rendering to real-world scenarios is bottlenecked by the limited realism and temporal coherence of existing synthetic datasets. To bridge this persistent domain gap, we introduce a large-scale, dynamic dataset curated from visually complex AAA games. Using a novel dual-screen stitched capture method, we extracted 4M continuous frames (720p/30 FPS) of synchronized RGB and five G-…
Symmetry and entanglement are two fundamental concepts in quantum many-body physics. Their interplay is captured by symmetry-resolved entanglement, which decomposes the total entanglement into contributions from different symmetry sectors. Computing symmetry-resolved entanglement in strongly interacting higher-dimensional quantum systems remains challenging. Here, we formulate and implement an estimator-based quantum…
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.
Early stopping treats training time as a capacity knob: halt when a validation metric stops improving so the model does not wander into overfit.
Hallucination is fluent generation that is not supported by the source or the world — a likelihood-trained model completing a pattern, not a database lookup.
PPO is a policy-gradient algorithm that clips the probability ratio so each update stays close to the previous policy, giving much of TRPO’s stability with first-order SGD.
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.
Vanishing gradients are when backprop multiplies many |Jacobian| < 1 factors so early layers receive ~0 update — the reason plain deep RNNs and tanh stacks died.
PD is the probability a name defaults over a horizon — real-world for books, risk-neutral for CDS.
Express views with listed options on futures — defined-risk directional, calendars, or vol — still a CTA if the underlying is a commodity interest.
Crude, products, natgas, and sometimes power or emissions — a complex with storage, geopolitics, and some of the nastiest gaps in the futures world.
Trend and overlays on ES, NQ, RTY, SX5E, NKY, EM indexes — the financial-CTA equity sleeve, not a stock-picker.
Currency futures and NDF/forwards — G10 trend, EM, and sometimes a carry overlay — the most liquid two-way sleeve in the complex.
Managed futures is the strategy category: client capital traded in a diversified futures universe, usually systematic trend, sometimes with carry, reversion, or macro overlays.
A price-based engine with a fundamental veto or tilt — inventories, COT, positioning, or nowcasts that can cut or flip a trend.
Trade the VIX curve as a first-class market — trend on VIX, carry on contango, and a respect for inversion — not just an equity hedge overlay.
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 call option is the right, not the obligation, to buy the underlying at a strike by expiry — convex upside for a premium.
Delta is the first derivative of option value to the underlying — the hedge ratio and a moneyness label.
Delta Hedging — Continuous rebalancing of directional exposure that links options markets to underlying liquidity.
Gamma is the sensitivity of delta to the underlying — how fast the hedge ratio moves, and who is chasing whom.
LEAPS Options — Long-dated equity options used for leveraged directional or hedge overlays.
Monte Carlo Option Pricing — Simulation pricing for path-dependent and multi-asset claims.
A put option is the right to sell the underlying at a strike — convex downside, or a hedge that costs carry.
The Triffin dilemma is the conflict of a reserve-currency issuer: the world needs the issuer to run liabilities (deficits) for reserve supply, but those deficits eventually undermine confidence in the reserve asset.
The 1992–93 ERM crisis (Black Wednesday in the UK) was a trilemma event: fixed parities, free capital, and a Bundesbank that would not ease for the periphery.
Lehman weekend (13–15 September 2008) was the disorderly failure of a primary dealer — the moment a housing/credit crunch became a global run on counterparties and money funds.
Sweden, Finland, and Norway’s early-1990s banking crises followed financial liberalization, a real-estate boom, and a peg-defense rate shock — a clean ‘credit boom gone wrong’ that ended in nationalization and bad banks.
The Plaza Accord was a coordinated 1985 G5 intervention to weaken the dollar after a brutal early-1980s USD squeeze — not a crash, but a regime change in FX that re-priced US manufacturing and later fed Japan’s bubble politics.
The US S&L crisis was a 1980s–early-1990s wave of thrift failures after rate shock, moral hazard, and regulatory forbearance — resolved by RTC at a large fiscal cost.
The 2013 taper tantrum was a fast global rates-and-EM selloff after Bernanke hinted at slowing QE — a rehearsal of how the world’s dollar duration is one speech.
Tulip mania was a 1636–37 Dutch futures craze in rare bulbs that collapsed in February 1637 — the template for a story-driven, lightly margined, socially contagious bubble.
A callable bond lets the issuer redeem early at a schedule of prices — you sold a call to the issuer and should be paid for it.
Distressed Debt Ratio — Share of debt trading at deep discounts — early warning for credit cycle turns.
Currency Reserves Adequacy — Whether EM authorities can defend pegs or smooth disorderly depreciations.
Foreign Exchange Intervention — Official buying or selling of currency to manage disorderly moves and imported inflation.
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 call option is the right, not the obligation, to buy the underlying at a strike by expiry — convex upside for a premium.
A callable bond lets the issuer redeem early at a schedule of prices — you sold a call to the issuer and should be paid for it.
Time equity beta with oil’s recent move or level — a macro overlay that treats crude as a growth/inflation signal.
Express views with listed options on futures — defined-risk directional, calendars, or vol — still a CTA if the underlying is a commodity interest.
Currency Reserves Adequacy — Whether EM authorities can defend pegs or smooth disorderly depreciations.
Delta is the first derivative of option value to the underlying — the hedge ratio and a moneyness label.
Delta Hedging — Continuous rebalancing of directional exposure that links options markets to underlying liquidity.
Distressed Debt Ratio — Share of debt trading at deep discounts — early warning for credit cycle turns.
Early stopping treats training time as a capacity knob: halt when a validation metric stops improving so the model does not wander into overfit.
Crude, products, natgas, and sometimes power or emissions — a complex with storage, geopolitics, and some of the nastiest gaps in the futures world.
Trend and overlays on ES, NQ, RTY, SX5E, NKY, EM indexes — the financial-CTA equity sleeve, not a stock-picker.
Factor Momentum — Persistence in relative factor performance exploitable by systematic overlays.
Foreign Exchange Intervention — Official buying or selling of currency to manage disorderly moves and imported inflation.
Currency futures and NDF/forwards — G10 trend, EM, and sometimes a carry overlay — the most liquid two-way sleeve in the complex.
Gamma is the sensitivity of delta to the underlying — how fast the hedge ratio moves, and who is chasing whom.
Hallucination is fluent generation that is not supported by the source or the world — a likelihood-trained model completing a pattern, not a database lookup.
Stay long industries with accelerating or extreme momentum — a trend overlay that explicitly rides (and must exit) industry bubbles.
Overweight small or beaten-up names in early January — the tax-loss / window-dressing calendar, heavily mined.
LEAPS Options — Long-dated equity options used for leveraged directional or hedge overlays.
Lehman weekend (13–15 September 2008) was the disorderly failure of a primary dealer — the moment a housing/credit crunch became a global run on counterparties and money funds.
Managed futures is the strategy category: client capital traded in a diversified futures universe, usually systematic trend, sometimes with carry, reversion, or macro overlays.
Time global equity exposure with calendar rules (Halloween, first-half vs second-half year) rather than a fundamental forecast.
Monte Carlo Option Pricing — Simulation pricing for path-dependent and multi-asset claims.