





 !"#$%


&$'$'()*+,* /
 !"#$
%&'(()()*+
'0*,/1231
"
,-$
./0000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000(
12$(343356789:93;6<83=>?@350 0A
(0(0@B9<89:93;6<83
=>?@3500000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000A
(0A089:93;6<83=>?@350000000000000000000000000000000000000000000C
12$ADEEFG000000000000000000000000000000000000000000000000000000000000000000000000000000000*
A0(0HIJK$LM0000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000*
A0A0LMNOPOQR!0000000000000000000000000000000000000000000000000000000000000000000000000000000*
A0S0LMNOPOQR!$#TAU1JIJ000000000000000000000000000000000000000000000000000V
A0S0(0WNOX$NOYZK[XZ\]000000000000000000000000000000000000000000000000000000000000000000000000000000000V
A0S0A0^H_ZZT[K000000000000000000000000000000000000000000000000000000000000000000000000000000000000000()
A0C0`aKNZb0000000000000000000000000000000000000000000000000000000000000000000000000000000()
A0c0ade-R`RZfgQSad000000000000000000000000000000000000000000000000000000(S
A0+0ade-h,ZKO000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000(S
12$S@i8FB:0000000000000000000000000000000000000000000000000000000000000000000000000000000000000(c
S0(0J0000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000(c

A
678*+3
9%% !"
3'3'$:";<%==%%
 !"
,Z$p$(VV)~`HTb$g"M&'ZK•K&'…-|$X•
X{${KadK~T{ZR…&KH,•e-|$$|$LKf
ƒ$I‘KfTsT~|$$,Os|$~’hU~h,hR%$…KKfR1-THO
a{ZH&Zb1ˆ$Me-Z$1ˆ0dLHZbR`$gXZ-~
2$L,a$ƒgZ-~$HZX„~,Os|$Rs…&Œ,ke-
THOa0•R…gQPLI{XpI${O{$IJ{Z$1ˆ}T,-HQU!
I1,p,Z$2&uXpI1U†$•~Rj-•0
•†T(VVV~HZ&1:0@OT-{H`$&e-|$ub_h,ghIhO
R%Q{'$gXpIR1k&,-‚$†T,Z{f0
8QPL  “ ,Z$†T A))A[A))S Y-TgLZ  u R!-“ http:www.sims.
berkeley.edu/research/projects/how-much-info-2003]~  Xp  I  Z{  f  †$  c
r€-UOh&Yc0()
(*
]0>pI†$AIf,Z$”$VH$0
p$&'Tƒ$e-&U•$t2&uXpI,Z$`&'$‚$
${O
[`&'XpI†gZ-
–r,ZUO—&6h,O@Z$_-&h@h3h,˜Z,ZTh,OY6@_3]
–(+ga†YTŒga(™$-U,$NOXpI0:NaXp
I,Z$Ac${O~gZXpIPHIJ{,†Th,-UOh&]0
[H2&uXpIgZ-
–{$,†UL…sge$U'
–h,g{$,d,‰KNq…-
–r(Z{,†T$-UOh&
[2&uXpI,Os|$

|$$gHTKH,ƒ•XpIR1kR!$j-I{&,a€d•Xp
Ip$|$paI{sTx{1-R1kUQRQ08-TzXpII{
T`U1JP-,$~I{PH,}gHTKH,ƒ•XpI08-TzXpI
R1kKNa{gLZ&H~KNaT`I1k$IJXpI‚TKH,-H
T‘ZœHIM…Ÿ$j-0
}(0AQuá trình khám phá tri thức
H,}gHTKH,ƒT|L,Z$}AI{T`PH,}IœKKƒbK~
&qX„$s2&uXpI~THO~K12$KHK'$g,Z$KNaXp

}(0( Lĩnh vực ứng dụng thành công của khai mỏ dự liệu
c
I~•!XpI~,ƒNbZ~‚T}T,-p$,ƒ•gZXpI
gt$I#0
}(0SCác lĩnh vực liên quan đến khám phá tri thức và khai mỏ dữ liệu
O,}gHTKH,ƒU-Z$#TSU1Jas€qIŸg-TzXpI
{RH$HgQPL0•T„Rs,-e-ƒ$X„$~uU1Js€qIŸ‰$-f

[MKkKXpI•$#XpIgH-0
[XpIfQZT„Rs,-~T‘~,1ˆ$XpI0
[_•X•XpI~O•Rtg•&-ZZK•kKJ$LMg-Tz
XpIT{U1JQKhZR1k&qX„$0
[@{T&bXpIg^K„R'J,1ˆ$XpI,Œ$~X1•-ZœXp
I,Œ$g|$kKI~…•$LTXpI20
-gR%Q{€qIŸXpI€Z$~RQU1Jg-TzXpIQ{
€NOX$HT|}J&Œ,ke-
–HO
–,aNbZ
–:NaXpIssU‚$K12$KHK'$g
–:12$KHK,P-•!XpI0
_1Jg-TzXpIR1k€hTI{U1J,$NTe-PH,}gHTKH,

{•R1kgQPL&,-0QgQPLg|$RbR1k&ZJT„Rs,-~
$1ˆ-…•P-OIbHU1Js€qIŸ-Og-TzXpIR•IœKIbPH,}
gHTKH,ƒ0
p$$LM,Z$()$LMP-,$,Z$g-TzXpIU-Z
$#T
(0 8IH$$s$
A0 _-UO$NO2
S0 NOPOQR!

w
C0 :12$KHKMKkKT|}1U-$$$~UZZ&$0
c0 •$$‘
+0 HO{•2Œ,k
w0 LM$ZT„Tgh-&
*0 @MgQkK…I{K,Z,0

*
678*+1&>??@A
NOPOQR!R1kUQ1I{{$Rf,Z$…T()$LMP-,$
e-g-TzXpI0
1'3'BCDEF+-G-H6IJH6KC
[8QPL&,-X•X!Y˜•h]0
[8HR2$L~-~PLR1k&qX„$s0
[@„,Z$s†TP-~NOPOQR1kU}I{$LMR1k
X•$sd{{|$d0
[LPOQHdRse-KNIZb~#P0
[@{TZXpI&'{IZb0
[1kƒ$X„${|$,Z$fQsKNaXpI~KNIZbh€~
&K-T~KNIZb$h0
[…,ds$LM& X„$YI-~(VVS]~Y~(V*C]0

.T‰R1kRH$HX-,KNaXpI'd…•
6RH$HX-,
[`Ik|$~˜Z,T-Z$-
[3˜Z,T-Z$-,-XZ
[“&'$~$Xh€Y]
`a{Z'¡
[Z,-gQPLI{NOzd0
[h,&&`a&,-H‰ŠK,h&‹fgQ0
[`IJ|$†$J$H,!,$U}fgQe-HMKZXp
IT{`a&,-0
[`a…Ik|$IJd0
`IJ|$
[|$R1kRZU‚$U&0

((
–ZT`KNK'€H€d~|$fQR•XRZHT`&gI{
h,ZKO0
–|$ƒah,ZKO
X*HY(FMZF
30
F
1
['F
*
\]F
3
D(+F
3
F
1

‰ŸIZ$)g|$€H
R!1$IZ$)I{)
(S
ŠTXO‹¤ŠZ,T-I‹
˜ZY¦+~(§]¤h,ZKOY+™w~(™w]¤[+™wIZ$Y+™w][(™wIZ$Y(™w]¤)0
R`Ik|$e-`aTXO
˜ZY¦V~c§][˜ZY¦S~C§~¦+~(§]¤)0VC)[)0w**¤)0(cA
`Ik|$|$e-H`a
Y,1JgKNZb][Y&-gKNZb]
Giải thuật học cây quyết định
$-Y¨IZZg¨]¤)0ACwU&
$-Y¨hTKh,-,]¤)0)AVU&
$-Y¨TXO¨]¤)0(cAU&
$-Y¨’XO¨]¤)0)C*U&
Kết quả
‰Ÿ…•‰IHg|$fgQ
:NZbX•$gXpIg|$•KNZb~%R1k$HZIJK
IJdƒ-,Z$‰IH0
1'^'V*6C6_HC`aOUO(H6Ib*c6 H&QHV*6C6_H

-YŠhTKh,-,h‹]¤)0cw(U&
-YŠ’XO‹]¤)0)A)U&
-YŠTXO‹]¤)0cw(U&
(C
[8(‰I{fgQ}R`RZU‚$)0
[8R`ŒIZbI{T-€T-I}R`RZfgQKLT-€T-I0
[`RZKL…adTI&-$h
Th-&,hY¦A~S~C§]¤Th-&,hY¦A~w§]–Yw™V]€Th-&,hY¦S~C§]
h,ZKOI{{Tz-T%Had,©
1'd'V*6C6_HC`aX*HY(FM

K,Z,R1kRs€dRfUu$,-\-I{H`$&ZK•KgHTKH,-
HT'IP-$p-HUQXpI0@MgQkKR1kƒ$X„$,ds,Z$
Q~I|‚T,Z$…TRfe-H$LMƒ$X„${|$e-g-
TzXpI0LM‡$$…KTœ{Z,Z$()$LMP-,$e-g-Tz
XpI0
Ví dụMKXpIƒ-H$-ZX!&-

(+
Q'1'BCOP*6*+6ga
,1Jg,}U{O$LMgQkK‰$-&£I{TPhHR!$j-
R1kX•$,Z$$LM0
–3hTœK`a¤$H,!-O$H,!06aX„~_~>~r0
–3hT&hIOMKHhT~aX„13¤ª~_~r«Yƒg|$P-,$]0
–,-&-ZY3>~hT&h]$-ZX!YTŒ$-ZX!I{(X”$]0
–KKZ,e-hT&h3R`Œ,k&KY3]I{&'I1k$e-H$-ZX!ƒ-30
>-,aX„,}
KYª~_~r«]¤A~&KYª_~«]¤C
–›,hPhhT&h3I{MK…&KKZ,'•I{TTT&KKZ,&KY3]¬¤
T&K0
–adMKZY&U&h]MKZe-(hT&h1ˆ$€O‡$
K{1ˆ$€O0

(w
Ví dụL&qª~_«I{˜,hPh~gR…&'If€de-L~_I{1ˆ$
€O¤¬•I{&'If€de-Zœ_‡$1ˆ$€O0dL
H$LMIMgQkKRsX-,ad&U&h0
@MgQkKXb$0
@MgQkK3hT&h(¤¬3hT&hA0
3hT&h(~Ag|$$-Z-{3hT&hAg|$,Œ$0
Ví dụ:~_¤¬r~{¤¬_~

_¤¬~rZ˜¤A™w¤A*¯°c)¯
¤¬~_~rZ˜A™V¤AA¯°c)¯
* Tìm luật mạnh
p$IM…&K¬¤T&K{Z˜¬¤TZ˜
&KY]¬¤T&K-XZ˜Y]¬¤TZ˜
Q'Q'-G-H6IJHDIJHc.H6hF
LMK,Z,gHTKHIMgQkK$#TAU1Ja}THMK
hT&h1ˆ$€O~&IM0
l1u$ae-$LM}THMKhT&h1ˆ$€O1&-
[qX„$MK([hTR•&,-MKA[hT~MKA[hTX•$R•&,-MKS[
hT~•
[QY_]I{˜,hPhhT&h~}Y]{Y_]KLI{1ˆ$€OhT&h&0
[QWI{˜,hPhg[hT&h~}dLYg[(][hT&U&h&e-W‡$I{
1ˆ$€O0
[ag[hT&hU‚$HTh,$hYg[(][hT&h&0
X 3hT&
( ~~>
A _~~r
S ~_~~r
C _~r
}S0(

(V
6aX„&-T-$LMK,Z,}THhT&h1ˆ$€OJ
T&K¤Ae-MKXpI1}S0(…C$-ZX!ƒ-HhTI{~_~~>~
r0_1J(~€HR!MK([hT&h…ƒ-(hT~&-R…UzHMKhT&h…R`Œ
,kz2A$pIb([hT&h1ˆ$€O1}S0A0
([hT&h &K
ª« A
ª_« S

ª_~« A
ª_~r« S
ª~r« A
&K¤A
&K¤A
A)
Ví dụZT`MKhT&h1ˆ$€O3¤ª_~~r«~&IMgQkK
…•I{
¤¬_~r
~_¤¬r
~r¤¬_
_¤¬~r
_~r¤¬
r¤¬~_
,Œ$¤¬~_~r
1ˆ$$LM}T,-,dsIMgQkK~…•I{HIMX1•-
g|$…Ÿ$j--OTN‘0•…R1kMKIM'~$1ˆ-1ˆ$KLHK
X„$HQI1kIIMgQkK0:12$KHK1ˆ$X•$X-,R`Œ,k
Yminsup]{R`MOe-IMYminconf]1R%,}U{O,Z$Kf$J
e-12$0W•IbaX„,~Q&qX„$minconf=70% }-“”IbAIM
1}S0c…R`MOIJ2minconf: R
2
(C, B
=>E),
R
3
(C, E
=>B).
IDXi (*j



A(
678*+T
o;4 !"p";%
T'3'6q*+H-f*VC6C`aH67O-f*HrZl/a-D\
[2$L~-…$~KadK0
[1ks$1ˆ&qX„$0
T'1'6q*+s_**W*C`aH67YBCZ$Fa/\
[LHZ~gXNT~KLR`$MTaI{p$T%R`bRagŽT0
[NOI%$Ka{KsZH0
T'Q'6q*+H6t*+cusvHw*H6_Hx(H67YBC+LMYa
[hZ$ƒZdOtd†TA)(AgZL$AžR|I-0
[`$ƒgHsH$()†TA))SgZL$()~CžR|I-0
[hZY>Z$~A))S]QT`$1ˆKHH1,HR1kIk()${R|
I-,Z$T`H$}1Ja&£$NOtdgZL$())${R|I-0
T'T'oH7y*+C`as-fCDKCH67YBC
[LTUJtdXZ1,HR1-,-
–@1,HX-,R!-“$1ˆ$u0
Dễ bị qua mặt, sinh ngẫu nhiên địa chỉ của người gởi.
–@1,HX-,•g…-
Dễ bị qua mặt: biến thể

AA
–@1,HX-,`X$
 `X$1Yg|$…d,‰]U•X•sd,‰UL$0
 |}‰•1RqXb$h2…$H,!{KfƒI{
f&'€d•ƒ3,Z$10
 MK1RqYUL$T-,M]~TŒX”$I{T`1~TŒ`12$
ƒ$JT`•,Z$•R•0
 WNOX$T|}KNIJK1,H~số chiều rất lớnRQ{„