Table 1:

SG features of trial t. ai, li, and dmpi denote the DM’s action, lottery result, and DM’s payoff in trial t, respectively. s(ht) is the average score of the suggested hotel in trial t, rt is its revealed review, and s(rt) is the revealed review score. * indicates that the feature is taken from Apel et al. (2020).

Feature NameFeature DescriptionFeature Formulation
Behavioral Features
HotelAcceptance Avg #trials where the hotel was accepted $∑i=1t−11{ai=1}t−1$
HotelAcceptance Earn Avg #trials where the hotel was accepted and the DM achieved a negative payoff.* $∑i=1t−11{ai=1∩dmpi>0}t−1$
HotelAcceptance Lose Avg #trials where the hotel was accepted and the DM achieved a positive payoff.* $∑i=1t−11{ai=1∩dmpi<0}t−1$
¬HotelAcceptance Earn Avg #trials where the hotel was not accepted but the payoff would have been positive if the DM had accepted it.* $∑i=1t−11{ai=0∩dmpi>0}t−1$
¬HotelAcceptance Lose Avg #trials where the hotel was not accepted but the payoff would have been negative if the DM had accepted it.* $∑i=1t−11{ai=0∩dmpi<0}t−1$
BadHotel Acceptance Avg #trials where a hotel with average score lower than 7.5 was accepted. $∑i=1t−11{ai=1∩s(hi)<7.5}t−1$
¬ExcellentHotel Acceptance Avg #trials where a hotel with average score higher than 9.5 was accepted. $∑i=1t−11{ai=0∩s(hi)>9.5}t−1$
DMPayoff Avg DM’s payoff pet trial $∑i=1t−1dmpit−1$

General Features
LotteryLow Avg #trials where the lottery result was lower than 3.* $∑i=1t−11{li<3}t−1$
LotteryMed Avg #trials where the lottery result was between 3 to 5.* $∑i=1t−11{li≥3∩li<5}t−1$
LotteryHigh Avg #trials where the lottery result was higher than 8.* $∑i=1t−11{li≥8}t−1$
CompletedTrials The proportion of trials that have already been played. $t−110$
GoodHotel Avg score of the current hotel is higher than 8.5. $1{s(ht)≥8.5}$
MedHotel Avg score of the current hotel is between 7.8 to 8.5. $1{s(ht)<8.5∩s(ht)≥7.5}$
BadHotel Avg score of the hotel is lower than 7.5. $1{s(ht)≤7.5}$
HighScore The attached score of the presented review is higher than 8.5. $1{s(rt)≥8.5}$
MedScore The attached score of the presented review is between 7.5 to 8.5. $1{s(rt)<8.5∩s(rt)≥7.5}$
LowScore The attached score of the presented review is lower than 7.5. $1{s(rt)<7.5}$
TopReview The attached score of the presented review is in the top 3 scoring reviews. $1{s(rt)∈top 3 scores}$
BottomReview The attached score of the presented review is not in the top 3 scoring reviews. $1{s(rt)∉top 3 scores}$
Feature NameFeature DescriptionFeature Formulation
Behavioral Features
HotelAcceptance Avg #trials where the hotel was accepted $∑i=1t−11{ai=1}t−1$
HotelAcceptance Earn Avg #trials where the hotel was accepted and the DM achieved a negative payoff.* $∑i=1t−11{ai=1∩dmpi>0}t−1$
HotelAcceptance Lose Avg #trials where the hotel was accepted and the DM achieved a positive payoff.* $∑i=1t−11{ai=1∩dmpi<0}t−1$
¬HotelAcceptance Earn Avg #trials where the hotel was not accepted but the payoff would have been positive if the DM had accepted it.* $∑i=1t−11{ai=0∩dmpi>0}t−1$
¬HotelAcceptance Lose Avg #trials where the hotel was not accepted but the payoff would have been negative if the DM had accepted it.* $∑i=1t−11{ai=0∩dmpi<0}t−1$
BadHotel Acceptance Avg #trials where a hotel with average score lower than 7.5 was accepted. $∑i=1t−11{ai=1∩s(hi)<7.5}t−1$
¬ExcellentHotel Acceptance Avg #trials where a hotel with average score higher than 9.5 was accepted. $∑i=1t−11{ai=0∩s(hi)>9.5}t−1$
DMPayoff Avg DM’s payoff pet trial $∑i=1t−1dmpit−1$

General Features
LotteryLow Avg #trials where the lottery result was lower than 3.* $∑i=1t−11{li<3}t−1$
LotteryMed Avg #trials where the lottery result was between 3 to 5.* $∑i=1t−11{li≥3∩li<5}t−1$
LotteryHigh Avg #trials where the lottery result was higher than 8.* $∑i=1t−11{li≥8}t−1$
CompletedTrials The proportion of trials that have already been played. $t−110$
GoodHotel Avg score of the current hotel is higher than 8.5. $1{s(ht)≥8.5}$
MedHotel Avg score of the current hotel is between 7.8 to 8.5. $1{s(ht)<8.5∩s(ht)≥7.5}$
BadHotel Avg score of the hotel is lower than 7.5. $1{s(ht)≤7.5}$
HighScore The attached score of the presented review is higher than 8.5. $1{s(rt)≥8.5}$
MedScore The attached score of the presented review is between 7.5 to 8.5. $1{s(rt)<8.5∩s(rt)≥7.5}$
LowScore The attached score of the presented review is lower than 7.5. $1{s(rt)<7.5}$
TopReview The attached score of the presented review is in the top 3 scoring reviews. $1{s(rt)∈top 3 scores}$
BottomReview The attached score of the presented review is not in the top 3 scoring reviews. $1{s(rt)∉top 3 scores}$
Close Modal