1. 1. Forecasting
a. “COUPON MANIAC”
b. It is a platform to sell online coupons, or what is also referred to as E-
commerce. With the goal of connecting buyers and sellers through prices and
variety of products and services.
Coupon Maniac is a national leader in local commerce, is the perfect place to
buy almost anything, anytime, anywhere, offers consumers a huge market for
great deals 24 hours. Buyers have the opportunity to discover the best of the
city and what it has to offer in the web or mobile. Coupon Maniac, has lots of
options like enjoying holiday or find a great selection in technology, fashion,
beauty, health, household items, with the advantage of paying by credit card
online or at retail outlets that help customers and businesses to operate more
efficiently. To find the best deals you must subscribe to Coupon Maniac with
email or visit the website.
c. Steps
1) The type efectuare is forecast that the demand forecast for monthly or yearly
how many units are that the plant must be able to produce to sell and also can
plan and transportation needs, inventories, etc.
2) The prognosis on women's footwear products
3) The time horizon is short-term, one-year projection analysis
4) Who employs forecasting model is Linear Regression
5) Historical sales data for women's footwear Virtual Store “Coupon Maniac”
3. 6) Forecasting
BOOTS Standard
Devation
Correlation
Coefficient
R^2
Linear
Regression
MONTHS 2011 2012 2013 2014 2015
JANUARY 765000 925000 1225000 1407000 1494000 311444 0.9700 1745200
FEBRUARY 742000 1032000 1303000 1498000 1555000 339133 0.9513 1853600
MARCH 756000 1125000 1363000 1504000 1578000 332932 0.9230 1872100
APRIL 800000 1134000 1390000 1500000 1600000 321909 0.9325 1874600
MAY 803000 1200000 1408000 1620000 1606000 339468 0.8905 1935200
JUNE 746000 1225000 1390000 1490000 1645000 344878 0.8946 1918100
JULY 732000 1301000 1405000 1505000 1680000 359531 0.8529 1954600
AUGUST 746000 1123000 1363000 1504000 1696000 367329 0.9640 1970700
SEPTEMBER 750000 1190000 1229000 1487000 305846 0.9020 1951500
OCTOBER 742000 1185000 1363000 1508000 332376 0.9249 2066100
NOVEMBER 731000 1223000 1299000 1522000 333576 0.8983 2050900
DECEMBER 1102000 1300000 1504000 1690000 254110 0.9997 2087800
2016
y= 244900x - 5E+08
R² = 0.8983
0
200000
400000
600000
800000
1000000
1200000
1400000
1600000
1800000
2000000
2010 2012 2014 2016
JANUARY
NOVEMBER
DECEMBER
Lineal
(NOVEMBE
R)
4. BOOTIES Standard
Devation
Correlation
Coefficient
R^2
Linear
Regression
MONTHS 2011 2012 2013 2014 2015 2016
JANUARY 730000 826000 964000 1366000 1355000 297000 0.9081 1585200
FEBRUARY 699000 873000 979000 1375000 1407000 312757 0.9402 1642000
MARCH 602000 904000 1126000 1400000 1442000 351399 0.9586 1747600
APRIL 655000 890000 1000000 1399000 1498000 353291 0.9650 1746900
MAY 725000 935000 1000000 1386000 1600000 355451 0.9586 1789500
JUNE 726000 907000 949000 1334000 1531000 331618 0.9433 1700500
JULY 745000 888000 946000 1355000 1426000 300860 0.9239 1620700
AUGUST 763000 904000 1026000 1390000 1470000 307368 0.9553 1680600
SEPTEMBER 737000 890000 1033000 1375000 272444 0.9501 1728700
OCTOBER 730000 874000 1042000 1388000 283311 0.9527 1758200
NOVEMBER 701000 895000 1050000 1402000 296622 0.9658 1802300
DECEMBER 1000000 1187000 1378000 1445000 200710 0.9634 1786600
0
500000
1000000
1500000
2000000
2010 2011 2012 2013 2014 2015 2016
JANUARY MARCH JUNE
5. HEELS Standard
Devation
Correlation
Coefficient
R^2
Linear
Regression
MONTHS 2011 2012 2013 2014 2015 2016
JANUARY 700000 703000 860000 903000 1190000 200232 0.8682 1225200
FEBRUARY 609000 692000 863000 943000 1050000 180370 0.9864 1171300
MARCH 610000 701000 802000 922000 1150000 210026 0.9593 1227300
APRIL 690000 686000 809000 971000 1064000 169140 0.9325 1153900
MAY 710000 790000 907000 1065000 1223000 207484 0.9829 1329300
JUNE 690000 653000 899000 951000 1039000 167830 0.8805 1145200
JULY 558000 600000 865000 927000 1111000 231784 0.9556 1242100
AUGUST 556000 620000 839000 911000 972000 182538 0.9462 1116500
SEPTEMBER 631000 625000 903000 953000 174421 0.8478 1213400
OCTOBER 697000 633000 860000 966000 151844 0.7728 1150900
NOVEMBER 702000 641000 900000 1000000 167753 0.7874 1214300
DECEMBER 830000 872000 1126000 1200000 183452 0.9214 1484400
7) Analysis
In the historical demand are included every month from 2011 to August 2015, online
sales of women's footwear product to be analyzed, classified according to type (boots,
booties and heels). With the information we proceeded to find the demand forecast
2016 for monthly or yearly how many units are that the plant must be able to produce
and thus also to plan transport needs, inventories, staff etc.
Having extensive information, start first by looking at the trend of growth in product
sales during the period, in this case it has been favorable growing and then checked to
y = 13626x +797515
R² = 0.3484
0
200000
400000
600000
800000
1000000
1200000
1400000
0 5 10 15
MONTHLY TREND
6. model the behavior of sales, which can be a linear model, log resembles etc. With the
help of the graph we see that the result of the sales actually describes a pattern of
upward growth
But if we analyze the monthly trend of each product is different because the behavior
changes detected in sales depending on the month, with a significant rebound from
May and December especially for trade in boots.
.