decision support and profit prediction for online auction
DESCRIPTION
Online auction has become a very popular e-commerce trans-action type. The immense business opportunities attract a lot of individuals as well as online stores. With more sellers engaged in, the competition between sellers is more intense. For sellers, how to maximize their pro¯t by proper auction setting becomes the critical success factor in online auction market. In this paper, we provide a selling recommendation service which can predict the expected pro¯t before listing and, based on the expected pro¯t, recommend the seller whether to use current auction setting or not. We collect data from ¯ve kinds of digital camera from eBay and ap- ply machine learning algorithm to predict sold probability and end-price. In order to get genuine sold probability and end-price prediction (even for unsold items), we apply probability calibration and sample selection bias correction when building the prediction models. To decide whether to list a commodity or not, we apply cost-sensitive analysis to decide whether to use current auction setting. We compare the pro¯ts using three di®erent approaches: probability-based, end-price based, and our expected-pro¯t based recommendation service. The experiment result shows that our recommendation service based on expected pro¯t gives higher earnings and probability is a key factor that maintains the pro¯t gain when ultra cost incurs for unsold items due to stocking.TRANSCRIPT
Authors / Chia-Hui Chang and Jun-Hong Lin
Presenter / Meng-Lun Wu
Decision Support and Profit Prediction for Online Auction
Sellers
1
OutlineINTRODUCTIONDATATO SELL OR NOT TO SELL?END-PRICE PREDICTIONSOLD PROBABILITY CALIBRATIONEXPRIMENTSCONCLUSIONS
2
INTRODUCTIONOnline auction has become a very popular
e-commerce transaction type.The main issue is to find an auction setting
that could maximize sellers profit is a challenging problem.profits prediction.
Ghani and Simmons apply three models for end-price prediction.regression, multi-class classification and
multiple binary classification.
3
INTRODUCTION (cont.)Some researchers suggest the use of
predicted end-price for selling strategy, but they didn’t address how to apply predicted end-price in decision making.
This paper proposed the use of cost-sensitive decision making to resolve whether to list a commodity or not.
Authors use profit gain over average profit of similar items sold by similar sellers.
4
DATAAuthors collect the digital cameras auction
data from eBays, and choose the period of two months in March-April 2006.
These data are classified into 3 classes:Seller Features, Items Features, Auction
Features
5
DATA (cont.)
6
DATA (cont.)
7
Two tasks
8
TO SELL OR NOT TO SELL?This paper have three approaches of
decision criteria:Sold probability Based Approach
When the predicted sold probability is greater than 50%.P(c=1|x) > P(c=-1|x)
End-price Based ApproachWhen the predicted end-price is higher than
the average end-price of similar itemsy(x) > Avgy(x)
9
TO SELL OR NOT TO SELL? (cont.)Expected profit Based Approach
When the expected profit gain for suggesting sell is greater than zero.
P(c=1|x)[Profit(x) – AvgP(x)]>P(c=-1|x)[lc(x)+uc]
10
END –PRICE PREDICTIONThere are two types of auction end-price
predictionsStatic : Multiple Binary ClassificationDynamic : Sample Selection Bias Correction
Ghani and Simmons proposed Multiple Binary Classification prediction method with neural network algorithm get the better accuracy.
Authors use multiple binary classifiers with two-class estimation to predict the end-price for auction listing items.
11
TWO–CLASS ESTIMATION
1247.5
Sample Selection Bias CorrectionSample selection bias problem has been
studied in econometrics and statistics.There are four kinds of sample selection
bias:Complete IndependentFeature BiasClass BiasComplete Bias
13
SOLD PROBABILITY CALIBATIONTo estimation the sold probability for an
item, we can use any binary classification to train a model for predicting whether an item would be sold (c=1) or not (c=-1).
In this paper, we use SVM as our classifier.SVM produces an uncalibrated value that is
not a probability.To yield well calibrated probability, we
adopt Platt Scaling to transfer a value f(xi) into probability P(c=1|xi).
14
EXPERIMENTS70% data as training data and 30% as
testing data.The experiments divided into three parts:
The performance on item sold predictionThe accuracy of end-price predictionCompares three performance of three
approachesProbability-basedEnd-price basedExpected profit based
15
Accuracy of Sold ProbabilityAuthors use SVM as our classifier for
predicting.The accuracy of prediction whether an item
will be sold I about 93.5% and 76.2% for auction listing and BuyItNow listing.
16
17
END-price PredictionTo use multiple binary classifiers for end-
price prediction, we need to decide the reference value for each binary classifier.
Authors exclude the highest and lowest end-prices, and use 10% window of the average end-price as the interval size.
18
19
20
Profit Gain ComparisonIn order to validate that end-price alone
does not guarantee high profit due to low sold probability, authors use profit gain over other sellers to compare the three approaches.
Sell all approach as the baseline for comparison.
21
Auction Listing
22
BuyItNow Listing
23
CONCLUSIONSA critical question for online auction sellers
is to find an auction setting.Authors apply machine learning algorithms
for end-price prediction and sold probability estimation.
For end-price prediction, since we can only use old items to train the classifiers, the model could under-estimate the end-price for unsold items.
24
CONCLUSIONS (cont.)As shown in the experiments, approaches
that don’t involve the consideration of sold probability have deteriorating profit as ultra cost increase.
This proves our argument that sold probability should also be considered for profit maximization.
The approach based on both probability and end-price have the best performances among all other approaches.
25