JP3400068B2 - Response amount prediction system - Google Patents
Response amount prediction systemInfo
- Publication number
- JP3400068B2 JP3400068B2 JP4846594A JP4846594A JP3400068B2 JP 3400068 B2 JP3400068 B2 JP 3400068B2 JP 4846594 A JP4846594 A JP 4846594A JP 4846594 A JP4846594 A JP 4846594A JP 3400068 B2 JP3400068 B2 JP 3400068B2
- Authority
- JP
- Japan
- Prior art keywords
- catalog
- response amount
- response
- predicted
- customer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Description
【発明の詳細な説明】
【０００１】
【産業上の利用分野】本発明は、カタログを顧客に送付
するときのレスポンス金額を予測するレスポンス金額予
測システムに関するものである。
【０００２】
【従来の技術】通信販売業は、昨年同時期に配布したカ
タログの実績をもとにカタログのレスポンス金額（受注
金額）およびレスポンス率（受注した顧客の割合）を予
測する。昨年と今年とでは景気・気候その他の違いがあ
り、昨年と同様の傾向を示すとは限らない。より正確な
予測をするために、大手通信販売業の多くは、本誌カタ
ログを発行する前に顧客の一部に対してプレカタログを
発刊している。このプレカタログを顧客先に送付してそ
のときの受注実績を参照して管理者が長年の感で今年の
本誌カタログの送付数などを決めていた。
【０００３】
【発明が解決しようとする課題】このため、正確なレス
ポンス金額を予測することができず、昨年と今年のプレ
カタログを送付したときの受注実績をもとにより正確な
レスポンス金額を予測する手段の提供が望まれていた。
【０００４】本発明は、これらの問題を解決するため、
過去と今回のプレカタログによるレスポンス金額（実
績）をもとに調整係数ｋを算出し、過去の顧客情報から
作成した回帰式などに予測対象の顧客情報を当てはめて
予測レスポンス金額を算出して当該調整係数ｋを加味し
た精度の高い予測レスポンス金額を算出し、カタログ送
付数を決定することを目的としている。
【０００５】
【課題を解決するための手段】図１は、本発明の原理ブ
ロック図を示す。図１において、レスポンス金額予測シ
ステム１は、過去の顧客情報６および予測対象の顧客情
報７をもとに予測レスポンス金額を算出し、これに過去
のプレカタログおよび予測対象のプレカタログのレスポ
ンス金額（実績）をもとに予測レスポンス金額を調整す
るものであって、レスポンス金額予測手段２、調整係数
算出手段３、および予測レスポンス金額算出手段４から
構成されるものである。
【０００６】レスポンス金額予測手段２は、過去の顧客
情報６をもとに作成した式６１に、予測対象の顧客情報
７を当てはめて予測レスポンス金額を算出するものであ
る。調整係数算出手段３は、今回のプレカタログのレス
ポンス金額（実績）９を過去のプレカタログのレスポン
ス金額（実績）８の差に対応する調整係数ｋを算出する
ものである。
【０００７】予測レスポンス金額算出手段４は、算出し
た予測対象の予測レスポンス金額に対して、調整係数ｋ
を加味した予測レスポンス金額を算出するものである。
過去の顧客情報６は、過去の顧客の受注実績などの顧客
情報である。
【０００８】予測対象の顧客情報７は、予測対象の顧客
情報である。過去のプレカタログのレスポンス金額８
は、過去のプレカタログを送付したときの顧客からのレ
スポンス金額（実績）である。
【０００９】予測対象のプレカタログのレスポンス金額
９は、予測対象のプレカタログを送付したときの顧客か
らのレスポンス金額（実績）である。予測レスポンス金
額１０は、予測対象の本誌カタログを送付するときの予
測したレスポンス金額である。
【００１０】
【作用】本発明は、図１に示すように、レスポンス金額
予測手段２が過去の顧客情報６をもとに作成した式６１
（例えば回帰式６１）に、予測対象の顧客情報７を当て
はめて予測レスポンス金額を算出し、調整係数算出手段
３が今回のプレカタログのレスポンス金額（実績）９を
過去のプレカタログのレスポンス金額（実績）８の差に
対応する調整係数ｋを算出し、予測レスポンス金額算出
手段４が算出した予測対象の予測レスポンス金額に対し
て調整係数ｋを加味した予測レスポンス金額を算出する
ようにしている。
【００１１】また、レスポンス金額予測手段２が過去の
顧客情報６をもとに作成した式６１（例えば回帰式６
１）に、予測対象の顧客情報７を当てはめて予測レスポ
ンス金額を算出し、調整係数算出手段３が今回のプレカ
タログのレスポンス金額（実績）９を過去のプレカタロ
グのレスポンス金額（実績）８で除算した調整係数ｋを
算出し、予測レスポンス金額算出手段４が算出した予測
対象の予測レスポンス金額に対して調整係数ｋを乗算し
た予測レスポンス金額を算出するようにしている。
【００１２】この際、過去のプレカタログの送付時期
と、今回のプレカタログの送付時期をほぼ同じにして、
変動要因を正確に予測するようにしている。従って、過
去と今回のプレカタログによるレスポンス金額（実績）
をもとに調整係数ｋを算出し、過去の顧客情報から作成
した回帰式６１などに予測対象の顧客情報を当てはめて
予測レスポンス金額を算出して当該調整係数ｋを加味し
た精度の高い予測レスポンス金額を算出することによ
り、より正確な予測レスポンス金額を算出してカタログ
送付数を決定することが可能となる。
【００１３】
【実施例】次に、図２から図４を用いて本発明の実施例
の構成および動作を順次詳細に説明する。
【００１４】まず、図２を用いてカタログ送付の全体の
動作を説明する。図２は、カタログ送付の全体説明図を
示す。図２において、Ｓ１は、カタログ企画する。これ
は、通信販売しようとする商品名、価格などを掲載する
カタログの企画をする。
【００１５】Ｓ２は、カタログ作成する。Ｓ３は、プレ
カタログを発刊する。これは、今年の本誌カタログを発
刊する前に、前年のプレカタログを発刊したと同一時期
に今年のプレカタログを発刊し、顧客からの受注を受
け、レスポンス金額およびレスポンス率などを算出し、
前年と今年との差（変動要因を数量的に把握する）を計
測するためのものである。
【００１６】Ｓ４は、調整係数を算出する。これは、Ｓ
３で今年のプレカタログを発刊したときの顧客から受注
を受け、集計したレスポンス金額（実績）と、前年の同
一時期のレスポンス金額（実績）との差、ここでは、今
年のレスポンス金額を前年のレスポンス金額で除算した
値（調整係数ｋ）を算出するものである（図３および図
４を用いて後述する）。
【００１７】Ｓ５は、レスポンス金額を予測する。これ
は、前年の本誌カタログ時の顧客情報をもとに予測した
予測対象の今年の本誌カタログ時の予測レスポンス金額
に対して、Ｓ４で算出した調整係数ｋを乗算したレスポ
ンス金額を予測する（図３および図４を用いて後述す
る）。
【００１８】Ｓ６は、顧客抽出する。これは、Ｓ５で予
測した今年の本誌カタログ時の予測レスポンス金額をも
とに、例えば所定予測レスポンス金額以上の本誌カタロ
グを送付する顧客を抽出する。
【００１９】Ｓ７は、ＤＭラベル発行する。これは、Ｓ
６で抽出した顧客の住所、氏名などをＤＭ（ダイレクト
メール）のラベルに印刷する。Ｓ８は、カタログ送付す
る。これは、Ｓ７でラベルを貼りつけた、あるいは顧客
の住所、氏名を印刷した封筒などを郵送する。
【００２０】Ｓ９は、発注を行う。これは、Ｓ８のカタ
ログを送付したことに対応して、カタログに掲載した商
品が間に合うように発注する。以上のカタログ送付の流
れの中で、Ｓ３からＳ５のレスポンス金額予測を行って
最適な顧客にカタログを送付する場合について以下図３
および図４を用いて詳細に説明する。
【００２１】図３および図４は、本発明の動作説明図を
示す。図３において、Ｓ１１は、過去の顧客情報６を準
備する。これは、予測しようとする対象と同時期の前年
の顧客情報６として、右側に記載した顧客情報を準備す
る。ここでは、例えば顧客Ａについて、図示のように、
・顧客Ａ
・９３年春号カタログ送付時 ９３年春号カタログに
対する受注実績
・最新購入日（ＸA1） ４３００円（ＹA）
・累計購入回数（ＸA2）
・最新購入金額（ＸA3）
・・・
・顧客Ｂ
・９３年春号カタログ送付時 ９３年春号カタログに
対する受注実績
・最新購入日（ＸB1） ０円（ＹB）
・累計購入回数（ＸB2）
・最新購入金額（ＸB3）
・・・
Ｓ１２は、サンプリング（ランダム）する。これは、Ｓ
１１の過去の顧客情報６からランダムにサンプリングす
る。
【００２２】Ｓ１３は、ランダムにサンプリングした後
の過去の顧客情報６である。Ｓ１４は、統計解析（数量
化理論１類）を行う。これは、右側に記載したように、
回帰式（全体に対して１つの式）を図示の下記のように
作成する。
【００２３】
Ｙ＝ａ0 ＋ａ1Ｘ1＋ａ2Ｘ2＋ａ3Ｘ3＋・・・
そして、過去の受注実績などを代入してａ0、ａ1、
ａ2、ａ3・・・を求める。Ｓ１５は、過去のレスポンス
金額を保存する。これは、Ｓ１３の過去の顧客情報６の
うちの過去の受注実績を、過去のレンスポンス金額とし
て保存したものである。
【００２４】Ｓ１６は、予測対象の顧客情報７を準備す
る。ここでは、９４年春号カタログ送付時点の予測対象
の顧客情報を準備する。Ｓ１７は、レスポンス金額の予
測を行う。これは、右側に記載したように、Ｓ１４で求
めた回帰式６１に、予測対象の顧客情報７を当てはめ、
顧客毎の予測レスポンス金額を求める。例えば右側に図
示のように、顧客ａ、ｂ・・・に対して、回帰式６１に
予測対象の顧客情報７中の当該顧客ａ、ｂ・・・の情報
を当てはめて予測レスポンス金額をそれぞれ求める。
【００２５】
Ｙa ＝ａ0＋ａ1Ｘa1＋ａ2Ｘa2＋ａ3Ｘa3＋・・・
Ｙb ＝ａ0＋ａ1Ｘb1＋ａ2Ｘb2＋ａ3Ｘb3＋・・・
・・・
Ｓ１８は、Ｓ１７で求めた、予測対象の顧客の予測レス
ポンス金額を保存したものである。
【００２６】図４において、Ｓ１９は、過去のプレカタ
ログのレスポンス金額（実績）である。これは、前年の
本誌カタログ発刊前のプレカタログを発刊してそのとき
の顧客からのレスポンス金額（実績）を保存したもので
ある。
【００２７】Ｓ２０は、今年の予測対象のプレカタログ
のレスポンス金額（実績）である。これは、今年の予測
対象の本誌カタログ発刊前のプレカタログを発刊してそ
のときの顧客からのレスポンス金額（実績）を保存した
ものである。
【００２８】Ｓ２１は、調整係数を算出する。これは、
右側に記載したように、
を算出する。これは、Ｓ２０で保存した予測対象のプレ
カタログのレスポンス金額（実績）をＳ１９で保存した
過去のプレカタログのレスポンス金額（実績）で除算し
て調整係数ｋを算出したものである。
【００２９】Ｓ２２は、調整係数ｋを加味した予測レス
ポンス金額を算出する。これは、Ｓ１８で保存した、予
測対象の今年の本誌カタログの予測対象の予測レスポン
ス金額に、Ｓ２１で算出した調整係数ｋを加味、例えば
乗算して変動要因を加味した予測レスポンス金額を算出
する。
【００３０】Ｓ２３は、Ｓ２２で算出した最終版の予測
レスポンス金額を保存したものである。Ｓ２４は、Ｓ２
３で保存した本誌カタログの調整係数ｋを加味した予測
レスポンス金額をもとにカタログ送付数の決定を行う。
例えば予測レスポンス金額が１０，０００円以上の顧客
（顧客数）に本誌カタログを送付すると決定する。
【００３１】以上によって、今年の同時期のプレカタロ
グのレスポンス金額（実績）を過去の同時期のプレカタ
ログのレスポンス金額（実績）で除算した調整係数ｋを
求め、前年の本誌カタログの顧客情報（実績）をもとに
作成した回帰式６１に今年の予測対象の顧客情報を当て
はめて予測レスポンス金額を算出し、これに調整係数ｋ
を乗算して今年の変動要因を加味した予測レスポンス金
額（最終版）を算出し、この予測レスポンス金額（最終
版）をもとに本誌カタログの送付数を決定する。これら
により、前年と今年の変動要因を加味したより正確な予
測レスポンス金額を算出し、的確なカタログ送付数を決
定することが可能となる。
【００３２】
【発明の効果】以上説明したように、本発明によれば、
過去の顧客情報６をもとに作成した回帰式６１に予測対
象の顧客情報７を当てはめて予測レスポンス金額を算出
し、この予測レスポンス金額に、前年と今年の同時期の
プレカタログのレスポンス金額（実績）から算出した調
整係数ｋを乗算して変動要因を加味した予測レスポンス
金額を求める構成を採用しているため、変動要因を加味
したより正確なレスポンス金額を予測ることができる。
そして、この算出した予測レスポンス金額を参照して、
予測レスポンス金額が例えば上位から８０％までの人数
の顧客にカタログを送付すると容易に決定できる。Description: BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a response amount prediction system for predicting a response amount when a catalog is sent to a customer. 2. Description of the Related Art A mail-order business predicts the response amount (order amount) and response rate (rate of ordered customers) of a catalog based on the results of catalogs distributed in the same period last year. There are differences in the economy, climate, and other factors between last year and this year, and the trends are not necessarily the same as last year. To make more accurate forecasts, many major mail-order companies publish pre-catalogs to some of their customers before publishing the catalog. The pre-catalog was sent to the customer, and the manager determined the number of catalogs to be sent this year with a long-term feeling by referring to the actual orders received at that time. [0003] For this reason, it is not possible to accurately predict the response amount, and to predict the accurate response amount based on the actual orders received when the pre-catalog was sent last year and this year. It was desired to provide a means for doing so. [0004] The present invention solves these problems,
The adjustment coefficient k is calculated based on the past and current pre-catalog response amounts (actual results), and the predicted response amount is calculated by applying the target customer information to the regression equation created from the past customer information and the like. The purpose is to calculate a highly accurate predicted response amount in consideration of the adjustment coefficient k and determine the number of catalogs to be sent. FIG. 1 is a block diagram showing the principle of the present invention. In FIG. 1, a response amount prediction system 1 calculates a predicted response amount based on past customer information 6 and predicted target customer information 7, and calculates a response amount of a past pre-catalog and a predicted target pre-catalog ( This is for adjusting the predicted response amount based on the (results), and includes a response amount predicting unit 2, an adjustment coefficient calculating unit 3, and a predicted response amount calculating unit 4. The response amount predicting means 2 calculates the predicted response amount by applying the customer information 7 to be predicted to the equation 61 created based on the past customer information 6. The adjustment coefficient calculating means 3 calculates an adjustment coefficient k corresponding to a difference between the response amount (actual) 9 of the current pre-catalog and the response amount (actual) 8 of the past pre-catalog. [0007] The predicted response amount calculating means 4 adds an adjustment coefficient k to the calculated predicted response amount.
Is added to calculate the predicted response amount.
The past customer information 6 is customer information such as a past customer order record. [0008] The customer information 7 to be predicted is customer information to be predicted. Past pre-catalog response amount 8
Is the response amount (actual result) from the customer when the past pre-catalog was sent. [0009] The response amount 9 of the pre-catalog to be predicted is the response amount (actual result) from the customer when the pre-catalog to be predicted was sent. The predicted response amount 10 is the predicted response amount when sending the journal catalog to be predicted. According to the present invention, as shown in FIG. 1, the response amount predicting means 2 generates an equation 61 based on past customer information 6.
The estimated response amount is calculated by applying the customer information 7 to be predicted to (for example, the regression equation 61), and the adjustment coefficient calculating means 3 converts the response amount (actual) 9 of the current pre-catalog into the response amount of the past pre-catalog ( An adjustment coefficient k corresponding to the difference of (actual result) 8 is calculated, and a predicted response amount in which the adjustment coefficient k is added to the predicted response amount of the prediction target calculated by the predicted response amount calculation means 4 is calculated. An equation 61 (for example, a regression equation 6) created by the response amount prediction means 2 based on the past customer information 6
The estimated response amount is calculated by applying the customer information 7 to be predicted to 1), and the adjustment coefficient calculating means 3 uses the response amount (actual) 9 of the current pre-catalog with the response amount (actual) 8 of the past pre-catalog. The divided adjustment coefficient k is calculated, and the predicted response amount is calculated by multiplying the predicted response amount calculated by the predicted response amount calculation means 4 by the adjustment coefficient k. At this time, the sending time of the past pre-catalog and the sending time of the present pre-catalog are almost the same,
We are trying to accurately predict fluctuation factors. Therefore, the past and current pre-catalog response amount (actual)
, An adjustment coefficient k is calculated based on the above, and the customer information to be predicted is applied to a regression equation 61 or the like created from past customer information to calculate a prediction response amount, and a highly accurate prediction response taking into account the adjustment coefficient k is calculated. By calculating the amount of money, it is possible to calculate a more accurate predicted response amount and determine the number of catalogs to be sent. Next, the configuration and operation of an embodiment of the present invention will be sequentially described in detail with reference to FIGS. First, the overall operation of sending a catalog will be described with reference to FIG. FIG. 2 is an overall explanatory diagram of catalog sending. In FIG. 2, S1 plans a catalog. This plans a catalog that lists the names and prices of products to be mail-ordered. In step S2, a catalog is created. S3 issues a pre-catalog. This means that before publishing this year's catalog, we publish this year's pre-catalog at the same time as the previous year's pre-catalog, receive orders from customers, calculate the response amount and response rate, etc.
This is to measure the difference between the previous year and this year (quantitatively grasp the fluctuation factors). In step S4, an adjustment coefficient is calculated. This is S
3. The difference between the total response amount (actual) and the response amount (actual) of the same period of the previous year received from the order received from the customer when the pre-catalog was published in this year. The value (adjustment coefficient k) divided by the response amount is calculated (described later with reference to FIGS. 3 and 4). In step S5, a response amount is predicted. This is to predict a response amount obtained by multiplying the predicted response amount at the time of this year's catalog, which is a prediction target, based on the customer information at the time of the previous year's catalog, by the adjustment coefficient k calculated at S4 (FIG. 3 and FIG. 4 to be described later). In step S6, customers are extracted. This is based on the predicted response amount at the time of this year's catalog catalog predicted in S5, and, for example, a customer who sends a journal catalog with a predetermined predicted response amount or more is extracted. In step S7, a DM label is issued. This is S
The address and name of the customer extracted in step 6 are printed on a DM (direct mail) label. In S8, the catalog is sent. This is done by mailing an envelope or the like on which the label is attached in S7 or on which the address and name of the customer are printed. In step S9, an order is placed. In this case, in response to the sending of the catalog in S8, an order is placed so that the products listed in the catalog can be received in time. FIG. 3 shows a case in which the response amount is predicted from S3 to S5 and the catalog is sent to the optimal customer in the flow of the catalog sending described above.
This will be described in detail with reference to FIG. FIG. 3 and FIG. 4 show operation explanatory diagrams of the present invention. In FIG. 3, S11 prepares past customer information 6. In this case, the customer information described on the right side is prepared as the customer information 6 of the previous year in the same period as the target to be predicted. Here, for example, for customer A, as shown in the figure, customer A, when the spring 1993 catalog was sent, actual order received for the spring 1993 catalog, latest purchase date (X A1 ) 4,300 yen (Y A ), and cumulative number of purchases (X A2 )-Latest purchase amount (X A3 ) ...-Customer B-When sending the Spring 1993 catalog Orders received for the Spring 1993 catalog-Latest purchase date (X B1 ) 0 yen (Y B )-Total number of purchases (X B2 )-Latest purchase amount ( XB3 ) ... In S12, sampling (random) is performed. This is S
Random sampling is performed from 11 past customer information 6. S13 is past customer information 6 after random sampling. In step S14, a statistical analysis (quantification theory 1) is performed. This, as described on the right,
A regression equation (one equation for the whole) is created as shown below. Y = a 0 + a 1 X 1 + a 2 X 2 + a 3 X 3 +... And a 0 , a 1 ,
a 2 , a 3 ... In step S15, the past response amount is stored. This is obtained by storing the past order results of the past customer information 6 in S13 as past response amounts. In step S16, customer information 7 to be predicted is prepared. Here, customer information to be predicted at the time of sending the spring 1994 catalog is prepared. In step S17, a response amount is predicted. This is, as described on the right side, by applying the customer information 7 to be predicted to the regression equation 61 obtained in S14,
Obtain the predicted response amount for each customer. For example, as shown on the right side, the predicted response amounts are obtained by applying the information of the customers a, b,... In the customer information 7 to be predicted to the regression equation 61 for the customers a, b,. . [0025] Y a = a 0 + a 1 X a1 + a 2 X a2 + a 3 X a3 + ··· Y b = a 0 + a 1 X b1 + a 2 X b2 + a 3 X b3 + ··· ··· S18 is , And S17, which stores the predicted response amounts of the customers to be predicted. In FIG. 4, S19 is the response amount (actual result) of the past pre-catalog. This stores a pre-catalog before the publication of the catalog of the previous year and stores the response amount (actual result) from the customer at that time. S20 is the response amount (actual) of the pre-catalog to be predicted this year. This is a publication of a pre-catalog before the publication of this year's catalog, which is the forecast target of this year, and stores the response amounts (actual results) from customers at that time. In step S21, an adjustment coefficient is calculated. this is,
As noted on the right, Is calculated. This is obtained by dividing the response amount (actual) of the pre-catalog to be predicted stored in S20 by the response amount (actual) of the past pre-catalog stored in S19 to calculate the adjustment coefficient k. In step S22, a predicted response amount taking into account the adjustment coefficient k is calculated. In this case, the predicted response amount calculated by adding the adjustment coefficient k calculated in S21 to the predicted response amount calculated in S21, for example, is added to the predicted response amount calculated in S21 to the predicted response amount calculated in S21 and stored in S18. In step S23, the predicted response amount of the final version calculated in step S22 is stored. S24 is S2
The number of catalogs to be sent is determined based on the predicted response amount in consideration of the adjustment coefficient k of the catalog stored in step 3 of the journal.
For example, it is determined that the journal catalog is sent to a customer (the number of customers) whose predicted response amount is 10,000 yen or more. As described above, the adjustment coefficient k obtained by dividing the response amount (actual) of the pre-catalog for the same period in this year by the response amount (actual) of the pre-catalog in the same period in the past is obtained, and the customer information ( The expected response amount is calculated by applying the customer information to be predicted this year to the regression equation 61 created based on the actual results), and the adjustment coefficient k is calculated.
Is calculated by taking into account the fluctuation factors of this year (final version), and the number of catalogs to be sent is determined based on the predicted response amount (final version). As a result, it is possible to calculate a more accurate predicted response amount in consideration of the fluctuation factors of the previous year and this year, and determine an accurate number of catalogs to be sent. As described above, according to the present invention,
The predicted response amount is calculated by applying the customer information 7 to be predicted to the regression equation 61 created based on the past customer information 6, and the response amount of the pre-catalog for the same period of the previous year and this year ( Since the configuration is adopted in which the predicted response amount taking into account the fluctuation factors is multiplied by the adjustment coefficient k calculated from the (actual result), a more accurate response amount taking into account the fluctuation factors can be predicted.
Then, referring to the calculated predicted response amount,
For example, it is possible to easily determine that a catalog is sent to customers whose predicted response amount is from the top to 80%.
【図面の簡単な説明】 【図１】本発明の原理ブロック図である。 【図２】カタログ送付の全体説明図である。 【図３】本発明の動作説明図（続く）である。 【図４】本発明の動作説明図（続き）である。 【符号の説明】 １：レスポンス金額予測システム ２：レスポンス金額予測手段 ３：調整係数算出手段 ４：予測レスポンス金額算出手段 ６：過去の顧客情報 ６１：回帰式 ７：予測対象の顧客情報 ８：過去のプレカタログのレスポンス金額（実績） ９：予測対象のプレカタログのレスポンス金額（実績） １０：予測レスポンス金額[Brief description of the drawings] FIG. 1 is a principle block diagram of the present invention. FIG. 2 is an overall explanatory diagram of catalog sending. FIG. 3 is an explanatory diagram (continued) of the operation of the present invention. FIG. 4 is an explanatory diagram (continued) of the operation of the present invention. [Explanation of symbols] 1: Response amount prediction system 2: Response amount prediction means 3: Adjustment coefficient calculation means 4: Expected response amount calculation means 6: Past customer information 61: Regression equation 7: Predicted customer information 8: Past pre-catalog response amount (actual) 9: Response amount of the pre-catalog to be predicted (actual) 10: Predicted response amount
───────────────────────────────────────────────────── フロントページの続き (56)参考文献 小泉修平，販売予測の全技術，ＰＨＰ 研究所，1994年 ３月15日，ｐ．153− 158 小林健吾，販売予測の知識，日本経済 新聞社，1993年 ７月 ９日，ｐ．41− 76，153−186 (58)調査した分野(Int.Cl.7，ＤＢ名) G06F 17/60 170 ＪＩＣＳＴファイル（ＪＯＩＳ)──────────────────────────────────────────────────続 き Continued on the front page (56) References Shuhei Koizumi, All Techniques of Sales Forecasting, PHP Research Institute, March 15, 1994, p. 153-158 Kengo Kobayashi, Knowledge of Sales Forecasts, Nihon Keizai Shimbun, July 9, 1993, p. 41-76, 153-186 (58) Field surveyed (Int. Cl. 7 , DB name) G06F 17/60 170 JICST file (JOIS)
Claims (1)
金額を予測するレスポンス金額予測システムにおいて、過去のカタログ送付時における、該カタログに対する受
注実績の情報である 顧客の受注実績と過去から現在まで
の顧客の情報である顧客情報とが記載された顧客データ
ベースと、 過去のプレカタログ送付時の顧客レスポンス率で今回の
プレカタログ送付時の顧客レスポンス率を除算し調整係
数を算出する調整係数算出手段と、 顧客データベースで過去の本カタログ送付時の顧客受注
実績と該過去の本カタログ送付時までの顧客情報とから
回帰式の各項目に係る係数を求め、現在までの顧客情報
と該回帰式の各項目に係る係数とから今回の本カタログ
送付時のレスポンス予測金額を算出し、前記レスポンス
予測金額に調整係数を乗算し、今回の調整後のレスポン
ス予測金額を算出するレスポンス金額算出手段とを有す
ることを特徴とするレスポンス金額予測システム。(57) [Claims] [Claim 1] In a response amount prediction system for predicting a response amount when a catalog is sent to a customer, a response to the catalog at the time of past catalog sending is provided.
Information on actual orders received from customers and past and present
And a customer database in which customer information as customer information is described, and an adjustment coefficient calculating means for calculating an adjustment coefficient by dividing the customer response rate at the time of sending the pre-catalog by the customer response rate at the time of sending the pre-catalog in the past From the customer database, a coefficient relating to each item of the regression equation is obtained from the past customer order reception results at the time of sending this catalog and the customer information up to the past sending this catalog, and the customer information up to the present and the regression equation Response amount calculating means for calculating a response estimated amount at the time of sending the present catalog from the coefficient relating to each item, multiplying the response estimated amount by an adjustment coefficient, and calculating a response estimated amount after the current adjustment. A response amount prediction system characterized by the following.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP4846594A JP3400068B2 (en) | 1994-03-18 | 1994-03-18 | Response amount prediction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP4846594A JP3400068B2 (en) | 1994-03-18 | 1994-03-18 | Response amount prediction system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPH07262167A JPH07262167A (en) | 1995-10-13 |
| JP3400068B2 true JP3400068B2 (en) | 2003-04-28 |
Family
ID=12804129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP4846594A Expired - Fee Related JP3400068B2 (en) | 1994-03-18 | 1994-03-18 | Response amount prediction system |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP3400068B2 (en) |
Families Citing this family (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA3027898C (en) | 2010-09-22 | 2023-01-17 | The Nielsen Company (Us), Llc | Methods and apparatus to determine impressions using distributed demographic information |
| CN103189856B (en) | 2011-03-18 | 2016-09-07 | 尼尔森（美国）有限公司 | The method and apparatus determining media impression |
| AU2013204865B2 (en) | 2012-06-11 | 2015-07-09 | The Nielsen Company (Us), Llc | Methods and apparatus to share online media impressions data |
| AU2013204953B2 (en) | 2012-08-30 | 2016-09-08 | The Nielsen Company (Us), Llc | Methods and apparatus to collect distributed user information for media impressions |
| US9519914B2 (en) | 2013-04-30 | 2016-12-13 | The Nielsen Company (Us), Llc | Methods and apparatus to determine ratings information for online media presentations |
| US10068246B2 (en) | 2013-07-12 | 2018-09-04 | The Nielsen Company (Us), Llc | Methods and apparatus to collect distributed user information for media impressions |
| US9313294B2 (en) | 2013-08-12 | 2016-04-12 | The Nielsen Company (Us), Llc | Methods and apparatus to de-duplicate impression information |
| US10333882B2 (en) | 2013-08-28 | 2019-06-25 | The Nielsen Company (Us), Llc | Methods and apparatus to estimate demographics of users employing social media |
| US10956947B2 (en) | 2013-12-23 | 2021-03-23 | The Nielsen Company (Us), Llc | Methods and apparatus to measure media using media object characteristics |
| US9852163B2 (en) | 2013-12-30 | 2017-12-26 | The Nielsen Company (Us), Llc | Methods and apparatus to de-duplicate impression information |
| US9237138B2 (en) | 2013-12-31 | 2016-01-12 | The Nielsen Company (Us), Llc | Methods and apparatus to collect distributed user information for media impressions and search terms |
| US10147114B2 (en) | 2014-01-06 | 2018-12-04 | The Nielsen Company (Us), Llc | Methods and apparatus to correct audience measurement data |
| US20150193816A1 (en) | 2014-01-06 | 2015-07-09 | The Nielsen Company (Us), Llc | Methods and apparatus to correct misattributions of media impressions |
| US9953330B2 (en) | 2014-03-13 | 2018-04-24 | The Nielsen Company (Us), Llc | Methods, apparatus and computer readable media to generate electronic mobile measurement census data |
| EP4219071A3 (en) | 2014-03-13 | 2023-08-09 | The Nielsen Company (US), LLC | Methods and apparatus to compensate impression data for misattribution and/or non-coverage by a database proprietor |
| US10311464B2 (en) | 2014-07-17 | 2019-06-04 | The Nielsen Company (Us), Llc | Methods and apparatus to determine impressions corresponding to market segments |
| US20160063539A1 (en) | 2014-08-29 | 2016-03-03 | The Nielsen Company (Us), Llc | Methods and apparatus to associate transactions with media impressions |
| US20160189182A1 (en) | 2014-12-31 | 2016-06-30 | The Nielsen Company (Us), Llc | Methods and apparatus to correct age misattribution in media impressions |
| US10045082B2 (en) | 2015-07-02 | 2018-08-07 | The Nielsen Company (Us), Llc | Methods and apparatus to correct errors in audience measurements for media accessed using over-the-top devices |
| US10380633B2 (en) | 2015-07-02 | 2019-08-13 | The Nielsen Company (Us), Llc | Methods and apparatus to generate corrected online audience measurement data |
| US9838754B2 (en) | 2015-09-01 | 2017-12-05 | The Nielsen Company (Us), Llc | On-site measurement of over the top media |
| US10205994B2 (en) | 2015-12-17 | 2019-02-12 | The Nielsen Company (Us), Llc | Methods and apparatus to collect distributed user information for media impressions |
| US10270673B1 (en) | 2016-01-27 | 2019-04-23 | The Nielsen Company (Us), Llc | Methods and apparatus for estimating total unique audiences |
-
1994
- 1994-03-18 JP JP4846594A patent/JP3400068B2/en not_active Expired - Fee Related
Non-Patent Citations (2)
| Title |
|---|
| 小林健吾，販売予測の知識，日本経済新聞社，１９９３年 ７月 ９日，ｐ．４１−７６，１５３−１８６ |
| 小泉修平，販売予測の全技術，ＰＨＰ研究所，１９９４年 ３月１５日，ｐ．１５３−１５８ |
Also Published As
| Publication number | Publication date |
|---|---|
| JPH07262167A (en) | 1995-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP3400068B2 (en) | Response amount prediction system | |
| Alfares | Inventory model with stock-level dependent demand rate and variable holding cost | |
| Jamal et al. | Optimal payment time for a retailer under permitted delay of payment by the wholesaler | |
| JP4154373B2 (en) | Power supply business risk management support system | |
| KR102066377B1 (en) | Delivery order management system interworking with multiple delivery brokerage servers | |
| KR101851498B1 (en) | System for real estate valuation | |
| Zhou et al. | An optimal replenishment policy for items with inventory-level-dependent demand and fixed lifetime under the LIFO policy | |
| Mattsson | Inventory control in environments with seasonal demand | |
| US20020194071A1 (en) | Reward system and apparatus used therefor | |
| Reiner et al. | Demand forecasting for supply processes in consideration of pricing and market information | |
| Vengatesan et al. | An approach of sales prediction system of customers using data analytics techniques | |
| Jewson et al. | The use of weather forecasts in the pricing of weather derivatives | |
| Pulido et al. | A continuous approximation model for locating warehouses and designing physical and timely distribution strategies for home delivery | |
| TW200300536A (en) | Sales forecasting apparatus and sales forecasting method | |
| JP2006221315A (en) | Management method of purchase cost difference and sales margin profit amount interlocking with exchange fluctuation | |
| Anjos et al. | Maximizing revenue in the airline industry under one-way pricing | |
| CN105825441A (en) | Catering industry material purchasing mobile terminal system | |
| JP2023133469A (en) | Information visualization processing apparatus, information visualization processing system, information visualization processing method, and information visualization processing computer program | |
| US20080172289A1 (en) | Automatic pricing measurement and analysis method and system | |
| Okoruwa et al. | Estimating sales for retail centers: an application of the Poisson gravity model | |
| Gjestland et al. | The suitability of hedonic models for cost-benefit analysis: Evidence from commuting flows | |
| JP6622678B2 (en) | Information processing apparatus, information processing method, and program | |
| JPH07239884A (en) | Purchasing and ordering system | |
| CN114626660A (en) | Method and apparatus for surge regulation forecasting | |
| JP7033325B2 (en) | Information visualization processing device, information visualization processing system, information visualization processing method, and information visualization processing computer program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 Effective date: 20030128 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20080221 Year of fee payment: 5 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20090221 Year of fee payment: 6 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20090221 Year of fee payment: 6 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20100221 Year of fee payment: 7 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20110221 Year of fee payment: 8 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20110221 Year of fee payment: 8 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20120221 Year of fee payment: 9 |
|
| LAPS | Cancellation because of no payment of annual fees |