平成○○年度知能システム科学専攻修士論文

Similar documents
johnny-paper2nd.dvi

kut-paper-template.dvi

130 Oct Radial Basis Function RBF Efficient Market Hypothesis Fama ) 4) 1 Fig. 1 Utility function. 2 Fig. 2 Value function. (1) (2)

, IT.,.,..,.. i

29 Short-time prediction of time series data for binary option trade

22 Google Trends Estimation of Stock Dealing Timing using Google Trends

4.1 % 7.5 %

Vol. 48 No. 4 Apr LAN TCP/IP LAN TCP/IP 1 PC TCP/IP 1 PC User-mode Linux 12 Development of a System to Visualize Computer Network Behavior for L

Japanese Journal of Family Sociology, 29(1): (2017)

〈論文〉組織改革の成果に関する予備的調査--社内カンパニー制導入が財務的業績に与える影響


SOM SOM(Self-Organizing Maps) SOM SOM SOM SOM SOM SOM i

16_.....E...._.I.v2006

Abstract This paper concerns with a method of dynamic image cognition. Our image cognition method has two distinguished features. One is that the imag

(1) i NGO ii (2) 112

( ) [1] [4] ( ) 2. [5] [6] Piano Tutor[7] [1], [2], [8], [9] Radiobaton[10] Two Finger Piano[11] Coloring-in Piano[12] ism[13] MIDI MIDI 1 Fig. 1 Syst

Vol.57 No.4 March 2008 : () 1 () () (1 ) (2 ) ( ) 1 Takagi (1989)Hamao (1992) (1998)

Vol. 23 No. 4 Oct Kitchen of the Future 1 Kitchen of the Future 1 1 Kitchen of the Future LCD [7], [8] (Kitchen of the Future ) WWW [7], [3

kiyo5_1-masuzawa.indd

..,,,, , ( ) 3.,., 3.,., 500, 233.,, 3,,.,, i

The 18th Game Programming Workshop ,a) 1,b) 1,c) 2,d) 1,e) 1,f) Adapting One-Player Mahjong Players to Four-Player Mahjong

Comparison of the strengths of Japanese Collegiate Baseball Leagues in past 30 seasons Takashi Toriumi 1, Hirohito Watada 2, The Tokyo Big 6 Baseball

n 2 n (Dynamic Programming : DP) (Genetic Algorithm : GA) 2 i

DPA,, ShareLog 3) 4) 2.2 Strino Strino STRain-based user Interface with tacticle of elastic Natural ObjectsStrino 1 Strino ) PC Log-Log (2007 6)

エンタープライズサーチ・エンジンQ u i c k S o l u t i o n ® の開発

THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE.

揃 Lag [hour] Lag [day] 35


2 194

わが国証券市場、証券業界の戦後70年

(a) 1 (b) 3. Gilbert Pernicka[2] Treibitz Schechner[3] Narasimhan [4] Kim [5] Nayar [6] [7][8][9] 2. X X X [10] [11] L L t L s L = L t + L s

わが国のコモディティ投資信託とETF

161 J 1 J 1997 FC 1998 J J J J J2 J1 J2 J1 J2 J1 J J1 J1 J J 2011 FIFA 2012 J 40 56

Web Stamps 96 KJ Stamps Web Vol 8, No 1, 2004

KII, Masanobu Vol.7 No Spring

_’¼Œì

2 ( ) i

卒業論文はMS-Word により作成して下さい

IPSJ SIG Technical Report Vol.2009-BIO-17 No /5/26 DNA 1 1 DNA DNA DNA DNA Correcting read errors on DNA sequences determined by Pyrosequencing

udc-4.dvi

ron.dvi

対朝鮮人絹織物移出と繊維専門商社の生産過程への進出

AtCoder Regular Contest 073 Editorial Kohei Morita(yosupo) A: Shiritori if python3 a, b, c = input().split() if a[len(a)-1] == b[0] and b[len(

soturon.dvi

258 5) GPS 1 GPS 6) GPS DP 7) 8) 10) GPS GPS ) GPS Global Positioning System

w.....I.v48.\1-4.eps

Bull. of Nippon Sport Sci. Univ. 47 (1) Devising musical expression in teaching methods for elementary music An attempt at shared teaching



Q [4] 2. [3] [5] ϵ- Q Q CO CO [4] Q Q [1] i = X ln n i + C (1) n i i n n i i i n i = n X i i C exploration exploitation [4] Q Q Q ϵ 1 ϵ 3. [3] [5] [4]

, (GPS: Global Positioning Systemg),.,, (LBS: Local Based Services).. GPS,.,. RFID LAN,.,.,.,,,.,..,.,.,,, i

- March IMF IMF IMF ITO The General Agreement on Tariffs and Trade

人工知能学会研究会資料 SIG-KBS-B Analysis of Voting Behavior in One Night Werewolf 1 2 Ema Nishizaki 1 Tomonobu Ozaki Graduate School of Integrated B

On Sapir's Principles of Historical Linguistics (I) An Interpretation on Sapir's View of Language Contact Nobuharu MIWA Abstract This paper is an atte

-March N ~ : National Statistical Office,n.d., Population & Housing Census Whole Kingdom National Statistical Office,, Population & Housing C

⑥中村 哲也(他).indd

先端社会研究 ★5★号/4.山崎

Tf dvi

評論・社会科学 84号(よこ)(P)/3.金子

スプレッド・オプション評価公式を用いた裁定取引の可能性―電力市場のケース― 藤原 浩一,新関 三希代

P2P P2P Winny 3 P2P P2P 1 P2P, i

149 (Newell [5]) Newell [5], [1], [1], [11] Li,Ryu, and Song [2], [11] Li,Ryu, and Song [2], [1] 1) 2) ( ) ( ) 3) T : 2 a : 3 a 1 :

58 10

DTN DTN DTN DTN i

206“ƒŁ\”ƒ-fl_“H„¤‰ZŁñ

1 [1, 2, 3, 4, 5, 8, 9, 10, 12, 15] The Boston Public Schools system, BPS (Deferred Acceptance system, DA) (Top Trading Cycles system, TTC) cf. [13] [

在日外国人高齢者福祉給付金制度の創設とその課題

1,000km 1.7% 0.0% 0.8% 100% 80% 60% 40% 20% 94.4% 0.1% 3.0% 0.3% 0.5% 0.0% 96.2% 1 0.2% 2.8% 0% km ft 40f

WASEDA RILAS JOURNAL

MPC MPC R p N p Z p p N (m, σ 2 ) m σ 2 floor( ), rem(v 1 v 2 ) v 1 v 2 r p e u[k] x[k] Σ x[k] Σ 2 L 0 Σ x[k + 1] = x[k] + u[k floor(l/h)] d[k]. Σ k x

1 1 tf-idf tf-idf i

IPSJ SIG Technical Report Vol.2011-EC-19 No /3/ ,.,., Peg-Scope Viewer,,.,,,,. Utilization of Watching Logs for Support of Multi-

13 RoboCup The Interface System for Learning By Observation Applied to RoboCup Agents Ruck Thawonmas


浜松医科大学紀要

Kyushu Communication Studies 第2号

DEIM Forum 2009 E

IPSJ SIG Technical Report Vol.2016-CE-137 No /12/ e β /α α β β / α A judgment method of difficulty of task for a learner using simple

The Effects of Tax Revenue by Deductions of National Income Tax and Individual Inhabitants Tax The national income tax and individual inhabitants tax

untitled

2 1 ( ) 2 ( ) i

Microsoft Word - ??? ????????? ????? 2013.docx

i

SPSS

Virtual Window System Virtual Window System Virtual Window System Virtual Window System Virtual Window System Virtual Window System Social Networking

14 2 5

11モーゲージカンパニー研究論文.PDF

_Y05…X…`…‘…“†[…h…•

地域総合研究第40巻第1号

,,.,,.,..,.,,,.,, Aldous,.,,.,,.,,, NPO,,.,,,,,,.,,,,.,,,,..,,,,.,

I II

21 Key Exchange method for portable terminal with direct input by user

Ł×

EQUIVALENT TRANSFORMATION TECHNIQUE FOR ISLANDING DETECTION METHODS OF SYNCHRONOUS GENERATOR -REACTIVE POWER PERTURBATION METHODS USING AVR OR SVC- Ju

:- Ofer Feldman,Feldman : -

ABSTRACT

<8ED089EF8B D312D30914F95742E696E6464>

〈論文〉中部圏構想の断章と高速自動車道の建設

23_02.dvi

untitled

Transcription:

A Realization of Robust Agents in an Agent-based Virtual Market Makio Yamashige 3 7

A Realization of Robust Agents in an Agent-based Virtual Market Makio Yamashige Abstract There are many people who try trading in stock by Artificial Intelligence approaches. However most of them have two problems. One is that they don't contain a risk-reducing method and the other is that their simulations depend only on the past price data to show their superiority. In this paper, I propose methods of trading in stock. These methods regard risk-reducing system as important. The risk-reducing system consists of two elements. One is to buy and sell at a safe price. The other is to manage stock position. Finally, I evaluate these methods in an agent-based virtual market, U-Mart.. U-Mart 3 U-Mart 4 5 7 8 9.

U-Mart U-Mart,3 U-Mart 3. U-Mart U-Mart U-Mart U-Mart U-Mart U-Mart

U-Mart 4. U-Mart 4 4.. 3 33 5 4.. 4... MMM Makio Matrix Method( MMM) MMM ( ) MMM n 3

% % MMM 4... A MMM 4

9% 4 MMM 5% 4 3 3 A 4..3. B A 4 B 4..4. C B,,,, % ( 5) MMM A 5

5 5 B 7 pi i p 38 39 ( ) pi K ( ) pi 39( ) p 4 i = pi i 4.3. 5 C 4.3.. NN: NN 4.3...9998594833 J3 99//99//3 NN A A 5. 5.. U-Mart 3

Shakur K.S S.S S.S S.I K.A K.A H.S T.M T.M S.K S.K S.K 3 Random S.S i ii K.A S.K Pre i ii 7 U-Mart 8 T.K Psychological MA 3% Osirator Y.N Y.N Y.N3 Random 3 4 998////4 77 J3TOPIX 99//997//3 MMM MMM 99//997//3 5.. 5... x

average _ profit( x) 77 i = profit( x, i) profit(x, i)x i standard_deviation(x) x average _ profit( x) sharp _ retio( x) standard_deviation(x) U-Mart average_ profit( x) profit _ loss _ retio min_ profit( x) min_profit(x)x 8 5... total _ value x= average _ profit( x) min_ profit min_profit min_profit(x)... 7 8 4 7 J3.8..4. -. 8 TOPIX

4 8 4 3.5.5 9 3 8 4 範 囲 外.5 J3 8 4 範範囲囲外外 TOPIX 8 4 範範囲囲外外.5 -.5 手法 A 手法 B 手法 C Shakur K.S S.S S.S S.I K.A K.A H.S K.A T.M S.K SK S.K 3 K.A T.K Psycological MA osirator Y.N Y.N Y.N 3 4.. A B NN A B B C NN 9

C NN C NN C AB NN C 7. 3 (CBOT) (CME) T-Bond (CBOT) 999/3999/999/9999/ /3/ 8. 8.. 5 7. -. -. -.3 手法 A 手法 B 手法 C 手法 NN 5 3 -. -. -.3 -.4 -.5 -. 手法 A 手法 B 手法 C 手法 NN.5.5 範 範 範 囲 囲 囲 外 外 外 手法 A 手法 B 手法 C 手法 NN 7 T-Bond

8.7..5.4.3.. 手法 A 手法 B 手法 C 手法 NN 8 NN 8.. A B U-Mart U-Mart 9. U-Mart A B A B C C U-Mart NN U-Mart U-Mart U-Mart

C U-Mart Vol.7, pp.4-74, 99 5 Norio Baba et al., A Hybrid Algorithm for Finding the Global Minimum of Error Function of Neural Networks and Its Applications, Neural Networks Vol.7 No.8, pp.53-5, 994 D,,, 999 7,,, 973 8, Pre U-Mart, 3, pp.3-8,, TOPIX - GAs&NNs, 7, pp.-, Koichi Kurumatani Yuhsuke Koyama Takao Terano Hajime Kita Akira Namatame Hiroshi Deguchi Yoshinori Shiozawa Hitoshi Matsubara, U-Mart: A Virtual Stock Market as a Forum for Market Structure Analysis and Engineering, Proceedings of the Fifth Joint Conference on Information Sciences, JCIS', Vol., pp.957-9, 3,, Vol.5 No., pp974-98, 4 Norio Baba Hisashi Handa Masaaki Hayashi, Utilization of neural networks and GAs for constructing an intelligent decision support system to deal stocks, Proceedings of SPIE Conference,