不動産webサービスを強くする機械学習の使い方

ෆಈ࢈XFCαʔϏεΛڧ͘͢Δ ػցֶशͷ࢖͍ํ ෆಈ࢈ςοΫษڧձ 5XJUUFS!IJEEZZ

͓໿ଋ ͜ͷ-5͸εϐʔΧʔݸਓͷ ݟղͰ͋Γɺॴଐ͢ΔاۀஂମΛ୅ද͢Δ΋ ͷͰ͸͋Γ·ͤΜɻ Disclaimer This LT expresses the viewpoints
of ME and is not reviewed for correctness or accuracy by my company.

*%!IJEEZZ ৬ۀɿ1.ʢϓϩμΫτͷ΄͏ʣ ͓࢓ࣄɿΨνίʔσΟϯάҎ֎ ಛٕɿXFCαʔϏεͮ͘Γ ɹͦΕඞཁʁͱݴ͍์ͭ ݴޠɿ3MFWFMͪΐͬ͜ͱSVCZSBJMT ઐ߈ɿܭྔܦࡁֶʢ541ʣ

͜Ε·Ͱ࡞ͬͨܞΘͬͨαʔϏε ohmy!Ո௞

௞ି෺݅৘ใαΠτΛ΍͍ͬͯ·͢

σʔλ෼ੳɺϏδϡΞϥΠθʔγϣϯʹΑΓɺ Ϣʔβʔ͕෺݅બͼΛ͠΍͘͢͢Δ

ࠓ೔͸-3௞ିͰͷ ػցֶशͷ ࢖͍ํΛ ͝঺հ͍ͨ͠

ڪΔ΂͖෺͕݅ଘࡏ͢Δ

͜ͷ΁Μ͸Θ͔Γ΍͍͢

͜ͷ΁Μ͸Θ͔Γ΍͍͢ ೖྗϛε

͜Ε͸ϗϯϞϊ

͜Ε͸χηϞϊ

Ո௞΍ؒऔΓɺ޿͞ͳͲͱ ͍Ζ͍Ζؔ࿈͍ͯ͠Δ

Ո௞΍ؒऔΓɺ޿͞ͳͲͱ ͍Ζ͍Ζؔ࿈͍ͯ͠Δ ͸͘͡ͷ͕ΊΜͲ͍͘͞

Ո௞΍ؒऔΓɺ޿͞ͳͲͱ ͍Ζ͍Ζؔ࿈͍ͯ͠Δ ͸͘͡ͷ͕ΊΜͲ͍͘͞ Ϟσϧͱ͔ߟ͑ͨ͘ͳ͍

0OFDMBTT47. TWN͞Μ͕ద౰ʹ֎Ε஋൑ఆͯ͘͠ΕΔ ڭࢣσʔλΛ༻ҙ͠ͳͯ͘ΠΠ Βͪ͘Μ

One-class svm library(kernlab) # make data to one-class svm model
DF <- data.frame(DF, class=1) outlier.svm <- ksvm(x=class ~bukken_shubetsu +struct +struct_all +madori +history_TOTAL +log_price_with_kanrihi, data=DF, type="one-svc",C=1000,scaled=TRUE,nu=0.01, kernel="rbfdot") #judge outlier DF$outlier <- predict(outlier.svm, DF, type = "response") ෺݅छผ ݐஙλΠϓ ઐ༗໘ੵ ؒऔΓ ங೥਺ ؅ཧඅࠐΈՈ௞ʢର਺Խʣ

Կ΋ߟ͑ͣ ߦ͘Β͍Ͱ ֎Ε஋͸͚ͨ͡ʂ 0 ʾ˜ʽ 0ƂŖŘ̇

ʢ໨తʣ ೖྗϛεσʔλͷ࡟ݮ ʢख๏ʣ "OPNBMZ%FUFDUJPO ʢํ๏ʣ 0OFDMBTT47.

͞ΒͳΔ໰୊

࢛৞൒ɺ෩࿊ແɺτΠϨڞಉɺτΩϫ૳ͷΑ͏ͳ෺݅

χʔζ͸ ͋Δ͔΋͠Εͳ͍

χʔζ͸ ͋Δ͔΋͠Εͳ͍ ʢ͕ͩʣ

͋·Γʹଟ͘ ϦετϖʔδʹͰΔͱ ݟͨ໨͕ѱ͍ɻɻ

ΑΖ͍͠ɺ ͳΒ͹ɺ ൑ఆثΛͭ͘Ζ͏

ಛघ෺݅ΛਓྗͰ݅ఔ౓ऩू ਓྗͰ໨ݟʂ ʢϋʔτΛڧ͘΋ͭ͜ͱʣ ˞෺݅ࣗମ͸ѱ͋͘Γ·ͤΜ

ಛघ෺݅ΛਓྗͰ݅ఔ౓ऩू ಛघ෺݅Ͱ͸ͳ͍΋ͷΛ݅நग़ ͜͜͸Կ΋ߟ͑ͳͯ͘΋ΠΠ

Boro detection svm library(kernlab) boro.svm <- ksvm( boro~bukken_shubetsu +struct +struct_all
+madori_num +madori_type_num +history_TOTAL +log_price_with_kanrihi, data=DF, C=1.584893, scaled=TRUE,nu=0.01, kernel="rbfdot",kpar=list(sigma=10),cross=13) ಛघ෺݅ΛਓྗͰ݅ఔ౓ऩू ಛघ෺݅Ͱ͸ͳ͍΋ͷΛ݅நग़ 47.ʹͯɺʮಛघ෺݅൑ఆثʯΛੜ੒ ෺݅छผ ݐஙλΠϓ ઐ༗໘ੵ ؒऔΓ ؒऔΓλΠϓ ؅ཧඅࠐΈՈ௞ʢର਺Խʣ ங೥਺ http://d.hatena.ne.jp/sleepy_yoshi/20120624/p1 Λνϡʔχϯάͷࢀߟʹ͠·ͨ͠

ಛघͳ෺͕݅ Ϧετ্Ґʹग़ͳͬͨ͘ʂ 0 ʾ˜ʽ 0ƂŖŘ̇

ʢ໨తʣ Ϧετϖʔδͷ69վળ ʢख๏ʣ ̎஋෼ྨث ʢํ๏ʣ 47.

਺ࣈ΋͍͋͛ͨͰ͢ ઌੜɻ

$73͕͋Βͳ͍͔ͳʔ ʢ͕͋Βͳ͍ʣ

ͦ͏͔ɺ $7ʢ໰߹ͤʣ͞ΕΔ ͨ ෺݅ʹ͸ͳʹ͔ಛ௃͕͋Δ ͷͰ͸ʁ

8FCϚʔέతΞϓϩʔνͩͱɺ ϢʔβʔηάϝϯτΛ͖Γɺ ରԠ͢Δ෺݅Λஸೡʹਫ਼౓ߴ͘ Ϩίϝϯυ͢Δͱ͜Ζ͕ͩɺɺɺ

ࡶʹ σʔλυϦϒϯͰ $73վળ͍ͤͨ͞

σʔλαΠΤϯςΟετϨϕϧද IUUQEIBUFOBOFKQTIBLF[P

Ϩϕϧ Ϩϕϧͷਓୡ͸ूܭ෼ੳʹՃ͑ͯɺ࠷௿ݶͷػցֶश ΍౷ܭֶͷख๏Λ஌͍ͬͯ·͢ɻ47.΍ϥϯμϜϑΥϨ ετͳͲͷϝδϟʔͳख๏Λ֮͑ɺσʔλ෼ੳ͕໘ന͘ ͳͬͯ͘ΔࠒͰ͢ɻ͔͠͠ͳ͕Β3΍4144ͳͲͷઐ༻ ιϑτΛৗʹσϑΥϧτઃఆͷύϥϝʔλͰ෼ੳ͍ͯ͠ ͨΓɺಛ௃ྔબ୒΍લॲཧͷॏཁੑΛ؁͘ݟΔ܏޲͕͋ Γ·͢ɻ ͍ۙ͏ͪʹݱ࣮ͷσʔλ͸JSJTͷΑ͏ʹ؁͘ͳ͍͜ͱΛ ஌Δ͜ͱʹͳΔͰ͠ΐ͏ɻ
  ͋Γ͕ͪͳൃݴ ʮϥϯμϜϑΥϨετ࠷ڧʯ

͋Γ͕ͪͳൃݴ ʮϥϯμϜϑΥϨετ࠷ڧʯ

ϥϯμϜϑΥϨετͰ $7͞Ε΍͍͢෺݅Λ༧ଌ

ϥϯμϜϑΥϨετͰ $7͞Ε΍͍͢෺݅Λ༧ଌ http://nakhirot.hatenablog.com/entry/20130704/1372874761 ΑΓൈਮ

ϥϯμϜϑΥϨετͰ $7͞Ε΍͍͢෺݅Λ༧ଌ CVͨ͠ ෺݅σʔλ CV͠ͳ͔ͬͨ ෺݅σʔλ 3BEPN 'PSFTU ʢύλʔϯೝࣝʣ ࠓ೔ͷ
෺݅σʔλ $7ͦ͠͏ͳ ෺݅σʔλʂ Πϝʔδ ֶश ֶश ༧ଌ

3ͷSBOHFSQBDLBHFͳΒ QSPCBCJMJUZ͕ग़ྗՄೳ install.packages('Rcpp') install.packages('ranger') # make CV model CV.ranger <-
ranger(formula = CV ~ walk_time1+struct+struct_all +level3+direction+madori_num+madori_type_num+price_with_kanrihi +history_TOTAL+station1+bukken_shubetsu+gyosha_no, data = DFtrain, num.trees=300, write.forest =TRUE, probability =TRUE, always.split.variables= "station1") # prediction of CV model cv.predict <- predict(CVmodel,DF) # draw probabilities cv.predict$predictions[,2]

$71SPCBCJMJUZͷߴ͍ ॱʹϦετදࣔ

$71SPCBCJMJUZͷߴ͍ ॱʹϦετදࣔ ޲্

ʢ໨తʣ $73վળ ʢख๏ʣ ̎஋෼ྨʢ$7֬཰Λܭࢉʣ ʢํ๏ʣ 3BOEPN'PSFTU RͩͱrangerͳͲ৽͍࣮͠૷͕Φεεϝʂʂ

ƅƁƅ Űŕ

ʮਓ޻஌ೳ࣌୅ʹඋ͑ͯ ෆಈ࢈ؔ࿈σʔλʹ͍ͭ ͯ৭ʑޠΒ͏ษڧձʯ

ਓ޻஌ೳͷఆٛ

ਓ޻஌ೳͷఆٛ %FFQ-FBSOJOHͰ ͳΜ͔Ͱ͖ͳ͍͔ͳʔ

%FFQ-FBSOJOH ͱ͍͑͹ը૾ղੳ

͜Ε·Ͱͷ෺݅αΠτʹ ͸ͳ͍ըظతػೳʂ

࿨ࣜτΠϨ൑ఆث

࿨ࣜτΠϨ൑ఆث ࿨ࣜτΠϨ͚ͩ͸ઈରʹݏͩʂ ͱݴ͏ਓ͸͖ͬͱ͍Δʹ͕͍ͪͳ͍

H2O Deeplearning library(h2o) # Deep learningͰֶशͤ͞Δ localH2O <- h2o.init(ip =
"localhost", port = 54321, startH2O = TRUE, nthreads=-1) res.dl <- h2o.deeplearning(x = 2:10001, y = 1, training_frame = as.h2o(target), activation = "TanhWithDropout", hidden=rep(160,5), epochs = 20) pred.dl <- h2o.predict(object=res.dl, newdata = as.h2o(target)) pred <- as.data.frame(pred.dl) # ਖ਼ղ཰Λ֬ೝ print(1-sum(abs(round(pred[,1]) - target[,1]))/length(target[,1])) ࿨ࣜτΠϨը૾ΛਓྗͰ݅ఔ౓ऩू ը૾αΠζΛἧ͑ͯɺάϨʔεέʔϧʹม׵ %FFQMFBSOJOHͰ࿨ࣜτΠϨ൑ఆثΛ࡞੒

H2O Deeplearning ਖ਼ղ཰ɿ ࿨ࣜτΠϨը૾ΛਓྗͰ݅ఔ౓ऩू ը૾αΠζΛἧ͑ͯɺάϨʔεέʔϧʹม׵ %FFQMFBSOJOHͰ࿨ࣜτΠϨ൑ఆثΛ࡞੒

ʢࠓ೔ͷ͓࿩ʣ ೖྗϛεσʔλ࡟আ ಛघ෺݅൑ఆ $73վળϑΟϧλ ࿨ࣜτΠϨ൑ఆث

΋ͬͱ෺݅બͼΛ ָ͍͠΋ͷʹͯ͠ ͍͖·͠ΐ͏ʂ

͋Γ͕ͱ͏͍͟͝·ͨ͠

不動産webサービスを強くする機械学習の使い方

不動産webサービスを強くする機械学習の使い方

Other Decks in Technology

Featured

Transcript