Jonli bozorlarda ishlaydigan savdo tizimlari bo'yicha tadqiqot.https://marketmaker.cc/uzhttps://marketmaker.cc/uz/blog/xgboost-gradient-boosting-trading/https://marketmaker.cc/uz/blog/xgboost-gradient-boosting-trading/Return-direction classifiers are imbalanced problems, and 0.5 is the wrong decision threshold. Comparing scale_pos_weight, focal loss, and precision-constrained threshold optimization on crypto data - plus the engineering differences between XGBoost, LightGBM, and CatBoost.Tue, 25 Aug 2026 00:00:00 GMTmachine-learningxgboostgradient-boostingquantpredictionhttps://marketmaker.cc/uz/blog/transfer-entropy-crypto-information-flow/https://marketmaker.cc/uz/blog/transfer-entropy-crypto-information-flow/DCC-GARCH tells you when crypto dependence tightens. Transfer entropy tells you which way it points. A directed information-flow measure, its null calibration, and an honest account of what it does and does not add over average pairwise correlation.Mon, 24 Aug 2026 00:00:00 GMTcausal-inferencetransfer-entropyinformation-theorycryptonetworkhttps://marketmaker.cc/uz/blog/trade-classification-algorithms/https://marketmaker.cc/uz/blog/trade-classification-algorithms/Reconstructing trade direction from OHLCV, bar history, or venues without an aggressor flag - the classic rules, the stale-quote problem, bulk volume classification, and how to measure them against crypto's free ground truth.Sun, 23 Aug 2026 00:00:00 GMTmicrostructuretrade-classificationLee-Readyorder-flowdeep-learninghttps://marketmaker.cc/uz/blog/tick-data-forecasting-deep-learning/https://marketmaker.cc/uz/blog/tick-data-forecasting-deep-learning/Sequence models fed tick data still assume regular spacing. Three ways to tell a Transformer when a tick actually happened - learnable-timescale continuous encoding, ODE-RNN latent state, and delta_t as a plain feature - and the ablation that decides between them.Sat, 22 Aug 2026 00:00:00 GMTHFTtick-datadeep-learninghigh-frequencypredictionhttps://marketmaker.cc/uz/blog/synthetic-control-trading-evaluation/https://marketmaker.cc/uz/blog/synthetic-control-trading-evaluation/This series has priced the selection route to a false edge - DSR prices the winner, PBO prices the search. Neither touches confounding: the strategy that made money because volatility doubled the week you deployed it. The Synthetic Control Method builds a weighted counterfactual from a donor pool of untouched instruments and gives you a falsification criterion and a placebo p-value.Fri, 21 Aug 2026 00:00:00 GMTcausal-inferencesynthetic-controlcounterfactualevaluationeconometricshttps://marketmaker.cc/uz/blog/probabilistic-forecasting-trading/https://marketmaker.cc/uz/blog/probabilistic-forecasting-trading/How to evaluate a predictive distribution honestly - CRPS as a proper scoring rule, the PIT histogram as a calibration diagnostic, and DeepAR sampling in GluonTS.Thu, 20 Aug 2026 00:00:00 GMTforecastingprobabilisticquantile-regressionDeepARuncertaintyhttps://marketmaker.cc/uz/blog/pinn-options-pricing/https://marketmaker.cc/uz/blog/pinn-options-pricing/Putting the Heston, free-boundary, and jump-diffusion pricing PDEs into a neural network loss - the log-price residual, the mixed-partial autograd trick, and what still needs measuring.Wed, 19 Aug 2026 00:00:00 GMTdeep-learningPINNoptionsBlack-ScholesPDEhttps://marketmaker.cc/uz/blog/pcmci-causal-discovery-crypto/https://marketmaker.cc/uz/blog/pcmci-causal-discovery-crypto/PCMCI ning ikki bosqichli MCI testi qanday qilib korrelyatsiya va ikki o'zgaruvchan Granger qila olmaydigan kripto aktivlari o'rtasidagi yo'naltirilgan sababiy bog'lanishni tiklaydi - qurilish, tigramit quvur liniyasi va unga hali kerak bo'lgan real ma'lumotlarni o'rganish.Tue, 18 Aug 2026 00:00:00 GMTcausal-inferencePCMCIcausal-discoverytime-seriescryptohttps://marketmaker.cc/uz/blog/order-flow-imbalance-prediction/https://marketmaker.cc/uz/blog/order-flow-imbalance-prediction/Xom kitob yangilanishlarini imzolangan oqim miqdoriga aylantirish: CKS hodisasining parchalanishi, PCA qisqarishi bilan ko'p darajali OFI va Lee-Ready savdo tasnifi - bundan tashqari, R-kvadrat sarlavhasi aslida nimani o'lchaganini halol hisobga olish.Mon, 17 Aug 2026 00:00:00 GMTmicrostructureorder-flowimbalancepredictionHFThttps://marketmaker.cc/uz/blog/neural-ode-continuous-finance/https://marketmaker.cc/uz/blog/neural-ode-continuous-finance/Neyron ODE'lar, Neyron SDE'lar va tartibsiz tanlangan bozor ma'lumotlari uchun doimiy normalizatsiya oqimlari - va uzluksiz dinamika ularning hal qiluvchi narxiga arziydimi yoki yo'qligini hal qiladigan bitta ablasyon.Sun, 16 Aug 2026 00:00:00 GMTdeep-learningneural-ODEcontinuous-timeSDEdynamicshttps://marketmaker.cc/uz/blog/multi-task-learning-trading/https://marketmaker.cc/uz/blog/multi-task-learning-trading/Qaytish, hajm va o'zgaruvchanlikni birgalikda bashorat qilish haqiqatan ham yordam beradimi? Yo'qotishlarni muvozanatlash sxemalarini o'lchash va gradient kosinus o'xshashligi orqali salbiy uzatish diagnostikasi - klassik asosiy chiziq va tozalangan oldinga burmalar bilan.Sat, 15 Aug 2026 00:00:00 GMTdeep-learningmulti-taskshared-representationpredictionauxiliaryhttps://marketmaker.cc/uz/blog/model-pruning-low-latency-trading/https://marketmaker.cc/uz/blog/model-pruning-low-latency-trading/Magnitude and structured pruning, the Lottery Ticket Hypothesis, movement pruning, distillation and 2:4 sparsity - the methods behind shrinking a trading model, and what still has to be measured before any of it ships.Fri, 14 Aug 2026 00:00:00 GMTmodel-compressionpruninglottery-ticketlatencydeploymenthttps://marketmaker.cc/uz/blog/liquidity-prediction-execution/https://marketmaker.cc/uz/blog/liquidity-prediction-execution/Our VWAP article shipped a static, weekly-refit volume curve and called the forecaster the weakest link. This is the follow-up: a Bayesian intraday updater run against the same 500-parent BTCUSDT harness, with the IS delta conditioned on realized curve error.Thu, 13 Aug 2026 00:00:00 GMTmicrostructureliquidityexecutionpredictionorder-bookhttps://marketmaker.cc/uz/blog/koopman-operator-market-dynamics/https://marketmaker.cc/uz/blog/koopman-operator-market-dynamics/Dynamic Mode Decomposition fits a linear operator to nonlinear market dynamics. The only question that matters: do the fitted modes persist from one window to the next, and does the rolling spectral radius lead realised volatility? Here is the measurement protocol and the code to run it.Wed, 12 Aug 2026 00:00:00 GMTmathematicsKoopmandynamical-systemsspectralpredictionhttps://marketmaker.cc/uz/blog/knowledge-distillation-trading-models/https://marketmaker.cc/uz/blog/knowledge-distillation-trading-models/The blog's standing answer to the accuracy-vs-latency tension is a two-stage fast/slow split. Distillation is a different answer: train one small model to mimic the ensemble. The KD loss, temperature, born-again nets, early exits for a variable latency budget, and the distill-to-FPGA pipeline - plus the measurements that would decide whether it beats the two-stage split.Tue, 11 Aug 2026 00:00:00 GMTmodel-compressiondistillationlatencyHFTdeploymenthttps://marketmaker.cc/uz/blog/instrumental-variables-quantitative-finance/https://marketmaker.cc/uz/blog/instrumental-variables-quantitative-finance/Selection bias in the search is not the only way a regression fools you. When the regressor is correlated with the error, more data makes the estimate more confidently wrong. Instrumental variables applied to the one endogeneity problem this blog has already left open: permanent impact from net taker flow.Mon, 10 Aug 2026 00:00:00 GMTcausal-inferenceinstrumental-variables2SLSeconometricsendogeneityhttps://marketmaker.cc/uz/blog/hawkes-process-order-arrival/https://marketmaker.cc/uz/blog/hawkes-process-order-arrival/Fitting a self-exciting point process to real crypto trade tape: where the three numbers (mu, alpha, beta) come from, how to estimate the branching ratio n, whether the exponential kernel survives a goodness-of-fit test, and how much n moves when you change the estimation window.Sun, 09 Aug 2026 00:00:00 GMTmicrostructureHawkes-processpoint-processorder-arrivalcryptoHFThttps://marketmaker.cc/uz/blog/hamiltonian-neural-networks-finance/https://marketmaker.cc/uz/blog/hamiltonian-neural-networks-finance/Hamiltonian Neural Networks are provably stable - but stability is worthless if the conserved quantity does not exist. Learning a scalar H via autograd, symplectic integration, and the falsification test that decides whether a financial (q, p) pair is canonical at all.Sat, 08 Aug 2026 00:00:00 GMTdeep-learningHamiltonianphysics-informeddynamicsconservationhttps://marketmaker.cc/uz/blog/granger-causality-lead-lag-crypto/https://marketmaker.cc/uz/blog/granger-causality-lead-lag-crypto/Granger causality on crypto prices done two ways - differenced returns and Toda-Yamamoto on levels - with a correct Wald implementation, an effective-N corrected causality matrix, and a rolling-stability test of whether the lag is tradeable at all.Fri, 07 Aug 2026 00:00:00 GMTcausal-inferenceGranger-causalitylead-lagcryptoVARhttps://marketmaker.cc/uz/blog/gaussian-processes-trading/https://marketmaker.cc/uz/blog/gaussian-processes-trading/Moliyaviy vaqt seriyalari uchun yadro dizayni - onaning pürüzlülüğü, mahalliy davriy tarkibi, spektral aralashmalar - va hech qanday tekshirish to'plamiga muhtoj bo'lmagan tartibga soluvchi sifatida chekli ehtimollik. Bundan tashqari, biron bir sotilishidan oldin o'lchanishi kerak bo'lgan narsalarning halol ro'yxati.Thu, 06 Aug 2026 00:00:00 GMTbayesiangaussian-processkerneluncertaintynon-parametrichttps://marketmaker.cc/uz/blog/fourier-neural-operator-finance/https://marketmaker.cc/uz/blog/fourier-neural-operator-finance/Operatorni o'rganish nuqtalarni emas, balki butun funktsiya bo'shliqlarini xaritalaydi - Furye Neyron Operatori chastotalar bo'shlig'ida PDE yechim operatorini qanday parametrlashtirgani, opsion narxlari uchun nimani sotib olishi va uning da'volaridan qaysi biri hali ham haqiqiy uskunada o'lchashga muhtoj.Wed, 05 Aug 2026 00:00:00 GMTdeep-learningFNOPDEoperator-learningoptionshttps://marketmaker.cc/uz/blog/flash-attention-trading-models/https://marketmaker.cc/uz/blog/flash-attention-trading-models/Flash Attention 23 400 bosqichli savdo kontekstini hisoblash uchun bepul qiladi - plitka qo‘yish, onlayn softmax va IO chegarasi N^2 d^2/M. Bu uzoqroq kontekst modelni yaxshiroq qiladimi yoki yo‘qmi, bu alohida savol va uni tasdiqlash emas, o‘lchash kerak.Tue, 04 Aug 2026 00:00:00 GMTdeep-learningattentionFlash-AttentionGPUoptimizationhttps://marketmaker.cc/uz/blog/ensemble-methods-trading/https://marketmaker.cc/uz/blog/ensemble-methods-trading/Savdo ansambllari haqida uchta narsa bu blogda yoritilmagan: nega modellar soni emas, kovariatsiya atamasi ansambl xatosida ustunlik qiladi, stacking oʻta meta-xususiyatlarga ega boʻlgan signal-kombinatsiya qatlami sifatida qanday ishlaydi va koʻplab signallar boʻylab aylanma tarmogʻi amalda bajarish narxini pasaytiradimi yoki yoʻqmi.Mon, 03 Aug 2026 00:00:00 GMTmachine-learningensemblebaggingstackingalphahttps://marketmaker.cc/uz/blog/double-ml-causal-trading/https://marketmaker.cc/uz/blog/double-ml-causal-trading/Bu blogdagi barcha modellar hozirgacha 'nimani nimani bashorat qiladi?' savolini javob beradi. Double ML 'nimaga nima sabab bo'ladi?' savolini javob beradi - himoya qila oladigan standart xato bilan. Qisman chiziqli model, Neyman ortogonaliteti, order book ma'lumotlarida tozalandirilgan cross-fitting va haqiqiy DML ishonch oralig'i faqat bitta oldindan belgilangan savolga nisbatan omon qolishiga oid sharhli hisobot.Sun, 02 Aug 2026 00:00:00 GMTcausal-inferencedouble-MLtreatment-effecteconometricsquanthttps://marketmaker.cc/uz/blog/causal-forests-treatment-effects-trading/https://marketmaker.cc/uz/blog/causal-forests-treatment-effects-trading/Ushbu blogdagi har bir backtest shartli o'rtacha qiymatni baholaydi. Kausal o'rmonlar buning o'rniga shartli davolash effektini baholaydi - tau(x) o'rniga mu(x) - vijdlan bo'linish, moslashuvchan yadro og'irliklari va topgan heterogennilik haqiqiymi yoki yo'qmi aytadigan kalibrlash testi bilan.Sat, 01 Aug 2026 00:00:00 GMTcausal-inferencecausal-forestheterogeneous-effectseconometricstreatmenthttps://marketmaker.cc/uz/blog/bayesian-neural-networks-trading/https://marketmaker.cc/uz/blog/bayesian-neural-networks-trading/Ushbu blogdagi har bir pozitsiya o'lcham qoida noaniqlikni bitta skalerga qisqartiradi. MC Dropout va chuqur ansambllar uni modelning bilmasligi va bozor shovqini sifatida ajratadi - va bu ikki turi turli pozitsiya o'lchamlarini nazarda tutadi.Fri, 31 Jul 2026 00:00:00 GMTbayesianuncertaintyneural-networkriskposition-sizinghttps://marketmaker.cc/uz/blog/automl-systematic-trading/https://marketmaker.cc/uz/blog/automl-systematic-trading/Avtomatlashtirilgan funksiyalarni yaratish (tsfresh, Featuretools), byudjetdan xabardor modellarni qidirish (FLAMLning tejamkor optimizatori) va WorldQuant formulali alfa zavodi - tadqiqot yoʻnalishining qismlari ushbu blogning qidiruv va haddan tashqari moslama yoyi hech qachon qamrab olinmagan va arcning oʻz natijalari ular haqida nima deydi.Thu, 30 Jul 2026 00:00:00 GMTAutoMLNASfeature-engineeringautomationquanthttps://marketmaker.cc/uz/blog/liquidation-cascades-trading-signal/https://marketmaker.cc/uz/blog/liquidation-cascades-trading-signal/Every leveraged position advertises the price at which it must be sold. How to build the on-chain liquidation depth chart and the CEX liquidation heatmap, model cascade dynamics as a reproduction number, and trade forced flow as a signal instead of only fearing it as a risk.Wed, 29 Jul 2026 00:00:00 GMTliquidationscascadetrading signaldefiperpetualsorder bookmarket microstructurecryptohttps://marketmaker.cc/uz/blog/uniswap-v3-lp-strategies-hedging/https://marketmaker.cc/uz/blog/uniswap-v3-lp-strategies-hedging/An active v3 LP is running a market-making book with gas costs and no cancel button. Size ranges from a GARCH vol forecast, frame rebalancing as fee-gain vs realized-cost, derive the position delta from tick math and hedge it with perps, and understand JIT liquidity and the honest pitfalls of backtesting LP from on-chain data.Tue, 28 Jul 2026 00:00:00 GMTuniswapdefimarket makingdelta hedginglvrjit liquidityquantethereumhttps://marketmaker.cc/uz/blog/mev-supply-chain-pbs-mevboost/https://marketmaker.cc/uz/blog/mev-supply-chain-pbs-mevboost/MEV stopped being a lone bot and became an assembly line: searcher, builder, relay, proposer. A technical walk through proposer-builder separation, MEV-Boost's sealed-bid block auction, why the searcher's margin gets bid away, order-flow auctions as the new moat, and how Solana's Jito model differs.Mon, 27 Jul 2026 00:00:00 GMTmevpbsmev-boostflashbotsjitoorder flow auctiondefiethereumhttps://marketmaker.cc/uz/blog/onchain-arbitrage-atomic-flash-loans/https://marketmaker.cc/uz/blog/onchain-arbitrage-atomic-flash-loans/On-chain arbitraj tsiklini topish - bu oson qism. Qiyin qism - bu xuddi shu tsiklni topgan boshqa har bir qidiruvchiga qarshi muhrlangan taklifli ustunlik auksionida g'alaba qozonish. Atomlik, flesh kreditlar, backrunning va arbitraj foydasi haqiqatan ham qayerda saqlanib qolishi - shu jumladan atomik bo'lmagan CEX-DEX haqida texnik tahlil.Sun, 26 Jul 2026 00:00:00 GMTarbitrajflesh kreditlarmevdefibackrunningcex-dexethereumatomlikhttps://marketmaker.cc/uz/blog/impermanent-loss-lvr-lp-profitability/https://marketmaker.cc/uz/blog/impermanent-loss-lvr-lp-profitability/Impermanent loss, konsentratsiyalangan likvidlik leveragi va qayta muvozanatlashga qarshi yo'qotish (loss-versus-rebalancing) birinchi tamoyillardan kelib chiqqan holda. Yopiq shakllar, σ²/8 natijasi, har bir blok bo'yicha markout va LP aslida HODLni mag'lub etadigan aniq to'lov-volatillik sharti.Sat, 25 Jul 2026 00:00:00 GMTdefiammimpermanent losslvruniswapmarket makingvolatilityquanthttps://marketmaker.cc/uz/blog/child-order-execution-tactics/https://marketmaker.cc/uz/blog/child-order-execution-tactics/Almgren-Chriss va VWAP faqat slice byudjetlarini belgilaydi - ijro esa taktika qatlamida qo'lga kiritiladi. Eskalatsiya taymerlari, maker-taker break-even matematikasi, Binance/OKX/CME'da amend va cancel-replace navbat semantikasi, iceberg anti-signaling va Python'dagi har-slice holat mashinasi.Fri, 24 Jul 2026 00:00:00 GMTijrochild orderorder taktikasinavbat pozitsiyasimaker-takericeberg ordermikrostrukturapythonhttps://marketmaker.cc/uz/blog/slippage-cost-models-backtest/https://marketmaker.cc/uz/blog/slippage-cost-models-backtest/Doimiy-bps slippage'ni order hajmiga, volatillikka va likvidlikka bog'liq xarajat egri chiziqlari bilan almashtiring: kvadrat ildiz qonuni, TCA fill'lari yoki ochiq ma'lumotlardan egri chiziqlarni moslash, rejim stress ko'paytiruvchilari va nima uchun strategiyangiz reytingi qayta aralashib ketadi.Thu, 23 Jul 2026 00:00:00 GMTslippagetranzaksiya xarajatlarimarket impactbacktestekzekutsiyatcakvadrat ildiz qonunixarajat modellarihttps://marketmaker.cc/uz/blog/smart-order-routing-crypto/https://marketmaker.cc/uz/blog/smart-order-routing-crypto/Nima uchun kriptoda SOR aksiyalar bozoridagi routingdan qiyinroq: yagona konsolidatsiyalangan tape yo'q, fantom likvidlik, kapitalni oldindan joylashtirish talabi. Matematika va Python bilan konveks routing optimizatsiyasi, maker-ga yo'naltirilgan taktikalar va o'z TCA'ingizdan olingan venue bo'yicha markout reytinglari.Wed, 22 Jul 2026 00:00:00 GMTexecutionsmart order routingmarket microstructurelikvidlik fragmentatsiyasikriptokvantpythontcahttps://marketmaker.cc/uz/blog/maker-taker-fees-rebates-execution/https://marketmaker.cc/uz/blog/maker-taker-fees-rebates-execution/Maker vs taker - bu komissiya jadvalini kiyib olgan adverse selection savdosi. Glosten-Milgrom orqali zararsizlik matematikasi, real kripto komissiya darajalari va token chegirmalari, reyt qaytarimini qazib olish tarixi, navbatga bog'liq reyt qiymati va backtestda pog'onali komissiyalarni modellashtirish.Tue, 21 Jul 2026 00:00:00 GMTmaker takersavdo komissiyalarireyt qaytarimlariadverse selectionmarket makingijrobozor mikrostrukturasibacktesthttps://marketmaker.cc/uz/blog/implementation-shortfall-tca-execution/https://marketmaker.cc/uz/blog/implementation-shortfall-tca-execution/Perold implementation shortfall tushunchasi kripto-botlar uchun ishlaydigan TCA quvuriga aylantirildi: kelish narxi bo'yicha dekompozitsiya, t+1s/10s/60s markout egri chiziqlari, o'z fill'laringiz ustida ~200 qatorli Python va natijalarni backtestingizning xarajat modeliga qaytarib berish.Mon, 20 Jul 2026 00:00:00 GMTijrotcaimplementation-shortfallmarkouttranzaksiya-xarajatlarialgotradingbacktestbozor-mikrostrukturasihttps://marketmaker.cc/uz/blog/onchain-liquidations-aave-compound/https://marketmaker.cc/uz/blog/onchain-liquidations-aave-compound/Aave v3 va Compound likvidatsiyalari amalda qanday ishlaydi: health factor matematikasi, close factor, likvidatsiya bonuslari, Chainlink oracle triggerlari va 2026-yilda flash-loan likvidatsiya botini ishga tushirish uchun nima kerak.Sun, 19 Jul 2026 00:00:00 GMTdefilikvidatsiyalaraavecompoundmevchainlinkflash loanlarkriptohttps://marketmaker.cc/uz/blog/uniswap-v3-concentrated-liquidity-quants/https://marketmaker.cc/uz/blog/uniswap-v3-concentrated-liquidity-quants/Uniswap v3 qanday ishlaydi: virtual zaxiralar, likvidlik L, sqrtPriceX96, tick matematikasi, feeGrowthInside va nega LP pozitsiyasi qisqa volatillik to'lovi hisoblanadi. Aniq formulalar va sonli misol bilan.Sat, 18 Jul 2026 00:00:00 GMTuniswapdefiammkontsentrlangan likvidlikmarket makinglvrkvantethereumhttps://marketmaker.cc/uz/blog/mev-sandwich-frontrunning-mempool/https://marketmaker.cc/uz/blog/mev-sandwich-frontrunning-mempool/Ochiq RPC'ga yuborgan har bir swap'ingiz - hech kim bajarishga majbur bo'lmagan ko'rinadigan limit order'dir. MEV extraction qanday ishlashining texnik tahlili: mempool tartiblash, Uniswap v2'da sendvich matematikasi, PGA'lar, Flashbots va treyder himoyasi.Fri, 17 Jul 2026 00:00:00 GMTmevsendvich hujumifrontrunningmempoolflashbotsdefiethereumhttps://marketmaker.cc/uz/blog/fill-simulation-partial-fills-backtest/https://marketmaker.cc/uz/blog/fill-simulation-partial-fills-backtest/Fill simulyatsiyasi ishonchliligining beshta pog'onasi - yopilish narxidagi fillardan ehtimollik asosidagi navbat pozitsiyasi modellarigacha. Qisman fillar holat mashinasi sifatida, limit-fill ehtimollik chegaralari PnL qamrovi sifatida va jonli fillarga qarshi kalibrlash tsikli.Thu, 16 Jul 2026 00:00:00 GMTfill simulyatsiyasibacktestlimit orderlarnavbat pozitsiyasiqisman fillarmarket makingijromarket mikrostrukturasihttps://marketmaker.cc/uz/blog/twap-vwap-pov-execution-algorithms/https://marketmaker.cc/uz/blog/twap-vwap-pov-execution-algorithms/TWAP, VWAP va POV - hajm prognoziga qo'yilgan tikishlardir. Biz har bir schedulerning yashirin taxminlarini tahlil qilamiz, kripto kun ichidagi hajm egri chiziqlarini quramiz va uchalasini qayta o'ynatilgan L2 ma'lumotlarida yuzma-yuz sinaymiz.Wed, 15 Jul 2026 00:00:00 GMTexecutiontwapvwappovimplementation-shortfallhajm-egri-chizig'ialgotradingbacktesthttps://marketmaker.cc/uz/blog/almgren-chriss-optimal-execution/https://marketmaker.cc/uz/blog/almgren-chriss-optimal-execution/Almgren-Chriss optimal ijro modelining to'liq xulosasi: chiziqli impact, sinh/cosh traektoriyasi, samarali chegara va Binance L2 hamda savdo ma'lumotlaridan eta, gamma va sigma parametrlarini kalibrlash uchun ishlaydigan Python kodi.Tue, 14 Jul 2026 00:00:00 GMTijroalmgren-chrissbozor ta'sirioptimal ijrotwapkvantpythonkriptohttps://marketmaker.cc/uz/blog/volatility-targeting-garch-strategy/https://marketmaker.cc/uz/blog/volatility-targeting-garch-strategy/GARCH volatillik prognozi faqat savdo qarorini yaxshilagandagina qadrga ega bo'ladi. Biz volatillikka yo'naltirilgan kripto strategiyasini quramiz, prognoz sifatini halol baholaymiz va walk-forward backtestda GARCHni realized-vol hamda EWMA bazaviy modellariga qarshi solishtiramiz.Mon, 13 Jul 2026 00:00:00 GMTvolatilityGARCHvolatility-targetingbacktestingriskcryptoalgorithmic-tradinghttps://marketmaker.cc/uz/blog/dcc-garch-dynamic-correlation-crypto/https://marketmaker.cc/uz/blog/dcc-garch-dynamic-correlation-crypto/Kripto korrelatsiyalar doimiy emas - har bir tushishda ular 1 ga tomon otilib chiqadi. DCC-GARCH vaqt bo'yicha o'zgaruvchan korrelatsiya matritsasini modellashtirib, pair savdo uchun dinamik hedge nisbatlarini va portfel riskini haqqoniy, vaqt bo'yicha o'zgaruvchan tarzda beradi.Sun, 12 Jul 2026 00:00:00 GMTvolatilityGARCHDCCcorrelationportfoliopairs-tradingcryptohttps://marketmaker.cc/uz/blog/asymmetric-garch-crypto-leverage/https://marketmaker.cc/uz/blog/asymmetric-garch-crypto-leverage/Oddiy GARCH(1,1) yaxshi va yomon yangiliklarni bir xil ko'rib, Gauss shoklarini faraz qiladi. EGARCH, GJR-GARCH va Student-t/skew-t innovatsiyalari ikkalasini ham tuzatadi - va kripto uchun haqiqiy VaR va Expected Shortfall beradi.Sat, 11 Jul 2026 00:00:00 GMTvolatilityGARCHEGARCHriskVaRcryptoalgorithmic-tradinghttps://marketmaker.cc/uz/blog/garch-volatility-forecasting-crypto/https://marketmaker.cc/uz/blog/garch-volatility-forecasting-crypto/GARCH(1,1) modeli kriptodagi o'zgaruvchanlik klasterlanishini qanday qamrab olishi, uni arch kutubxonasi yordamida maksimal ehtimollik bilan qanday moslashtirish va shartli-dispersiya bashoratlarini pozitsiya hajmi hamda dinamik stoplarga qanday aylantirish.Fri, 10 Jul 2026 00:00:00 GMTvolatilityGARCHriskforecastingcryptoalgorithmic-tradinghttps://marketmaker.cc/uz/blog/honest-negative-no-robust-edge/https://marketmaker.cc/uz/blog/honest-negative-no-robust-edge/Qidiruv va overfitting haqidagi yoʻnalishning yakuniy maqolasi - va u salbiy natija bilan tugaydi, bu esa aynan toʻgʻri natija. ETHUSDT ustida bitta simvolli, ikki taymfreymli qidiruv out-of-sample testda +16.35% va tegilmagan holdoutda +2.62% beradigan konfiguratsiyani topdi; ~37,000 sinovni hisobga olgan Deflyatsiyalangan Sharp koeffitsienti uni 0.00 gacha deflyatsiya qildi. Beshta yetakchi koin (ETH/BTC/SOL/BNB/XRP, har biri ~1.18M 1m bar) boʻyicha, out-of-sample medianasi asosida tanlaydigan kross-instrumental sinov uni uzil-kesil yoʻq qiladi: ikki taymfreymda DSR 0.24 / PBO 0.264, uch taymfreymda DSR 0.14 / PBO 0.327 - ikkalasi ham geytlardan oʻtmaydi. Chempion 5 simvoldan 1 tasida foydali, qolganlarida salbiy. Anti-overfit apparati aynan shu uchun kerak: shovqinning eng yaxshisini alfa sifatida ishga tushirishingizga yoʻl qoʻymaslik uchun.Thu, 09 Jul 2026 00:00:00 GMTalgotreydingbektestoverfittingdeflated-sharpepbosalbiy-natijavalidatsiyahttps://marketmaker.cc/uz/blog/proving-no-lookahead-multi-timeframe/https://marketmaker.cc/uz/blog/proving-no-lookahead-multi-timeframe/Ko'p vaqt oralig'idagi (multi-timeframe) bektestlar hali yakuniy yopilish narxi mavjud bo'lmagan, shakllanayotgan yuqori vaqt oralig'idagi bar orqali kelajakni sizib chiqaradi. Kodni ko'rib chiqish orqali ishonchga erisha olmaysiz - buni sinab ko'rish kerak. Biz jonli botning yopiq-bar qoidasini aynan takrorlaymiz, so'ngra kelajakni siljitadigan tekshiruv bilan sizib chiqishning yo'qligini isbotlaymiz: kelajakdagi har bir barni buzamiz va o'tmishdagi har bir signal hamda savdo bit-baytiga o'zgarmasligini tasdiqlaymiz. 25/25 paritet tekshiruvlari, va tekshiruvning haqiqiy tishi bor.Wed, 08 Jul 2026 00:00:00 GMTalgotradingbektestkelajakka qarash biasko'p vaqt oralig'ima'lumot sizib chiqishivalidatsiyahttps://marketmaker.cc/uz/blog/when-gpu-pays-off-sweep-roofline/https://marketmaker.cc/uz/blog/when-gpu-pays-off-sweep-roofline/GPUning CPUdan ustunligi paket hajmi bilan o'sadi - ko'p taymfreymli indikatorlarni oldindan hisoblashimizda har chaqiruvga bitta kombinatsiyada 54.5x dan 61 tasida 359.6x gacha - chunki kichik qidiruv kernelni ishga tushirish va uzatish ustamasini amortizatsiya qila olmaydi. Sarlavhadagi 167x ni CPUga ham naf keltiradigan 27x algoritmik yutuq karra 6.2x apparat yutug'iga ajratamiz, GPUning eng yaxshi CPUdan haqiqiy ustunligi bitta taymfreymda atigi 3.2x, ko'p taymfreymda 6.2x ekanini ko'rsatamiz va GPU sotib olish o'zini oqlashi uchun qidiruv qanchalik keng bo'lishi kerakligi haqida qaror qo'llanmasini beramiz.Tue, 07 Jul 2026 00:00:00 GMTalgotradingbacktestunumdorlikgpurooflineoptimallashtirish