MeDaScIn2016Hyndman.pdf

Transcript

1. Rob J Hyndman Automatic FoRecasting using R
2. Outline 1 Forecasting the PBS 2 Exponential smoothing 3 ARIMA models 4 TBATS models 5 Hierarchical time series Automatic FoRecasting using R Forecasting the PBS 2
3. Forecasting the PBS Automatic FoRecasting using R Forecasting the PBS 3
4. Forecasting the PBS The Pharmaceutical Benefits Scheme (PBS) is the Australian government drugs subsidy scheme. Many drugs bought from pharmacies are subsidised to allow more equitable access to modern drugs. The cost to government is determined by the number and types of drugs purchased. Currently nearly 1% of GDP ($14 billion). The total cost is budgeted based on forecasts of drug usage. Automatic FoRecasting using R Forecasting the PBS 4
5. Forecasting the PBS The Pharmaceutical Benefits Scheme (PBS) is the Australian government drugs subsidy scheme. Many drugs bought from pharmacies are subsidised to allow more equitable access to modern drugs. The cost to government is determined by the number and types of drugs purchased. Currently nearly 1% of GDP ($14 billion). The total cost is budgeted based on forecasts of drug usage. Automatic FoRecasting using R Forecasting the PBS 4
6. Forecasting the PBS The Pharmaceutical Benefits Scheme (PBS) is the Australian government drugs subsidy scheme. Many drugs bought from pharmacies are subsidised to allow more equitable access to modern drugs. The cost to government is determined by the number and types of drugs purchased. Currently nearly 1% of GDP ($14 billion). The total cost is budgeted based on forecasts of drug usage. Automatic FoRecasting using R Forecasting the PBS 4
7. Forecasting the PBS The Pharmaceutical Benefits Scheme (PBS) is the Australian government drugs subsidy scheme. Many drugs bought from pharmacies are subsidised to allow more equitable access to modern drugs. The cost to government is determined by the number and types of drugs purchased. Currently nearly 1% of GDP ($14 billion). The total cost is budgeted based on forecasts of drug usage. Automatic FoRecasting using R Forecasting the PBS 4
8. Forecasting the PBS In 2001: $4.5 billion budget, under-forecasted by $800 million. Thousands of products. Seasonal demand. Subject to covert marketing, volatile products, uncontrollable expenditure. Although monthly data available for 10 years, data are aggregated to annual values, and only the first three years are used in estimating the forecasts. All forecasts being done with the FORECAST function in MS-Excel! Automatic FoRecasting using R Forecasting the PBS 5
9. Forecasting the PBS In 2001: $4.5 billion budget, under-forecasted by $800 million. Thousands of products. Seasonal demand. Subject to covert marketing, volatile products, uncontrollable expenditure. Although monthly data available for 10 years, data are aggregated to annual values, and only the first three years are used in estimating the forecasts. All forecasts being done with the FORECAST function in MS-Excel! Automatic FoRecasting using R Forecasting the PBS 5
10. Forecasting the PBS In 2001: $4.5 billion budget, under-forecasted by $800 million. Thousands of products. Seasonal demand. Subject to covert marketing, volatile products, uncontrollable expenditure. Although monthly data available for 10 years, data are aggregated to annual values, and only the first three years are used in estimating the forecasts. All forecasts being done with the FORECAST function in MS-Excel! Automatic FoRecasting using R Forecasting the PBS 5
11. Forecasting the PBS In 2001: $4.5 billion budget, under-forecasted by $800 million. Thousands of products. Seasonal demand. Subject to covert marketing, volatile products, uncontrollable expenditure. Although monthly data available for 10 years, data are aggregated to annual values, and only the first three years are used in estimating the forecasts. All forecasts being done with the FORECAST function in MS-Excel! Automatic FoRecasting using R Forecasting the PBS 5
12. Forecasting the PBS In 2001: $4.5 billion budget, under-forecasted by $800 million. Thousands of products. Seasonal demand. Subject to covert marketing, volatile products, uncontrollable expenditure. Although monthly data available for 10 years, data are aggregated to annual values, and only the first three years are used in estimating the forecasts. All forecasts being done with the FORECAST function in MS-Excel! Automatic FoRecasting using R Forecasting the PBS 5
13. PBS data Automatic FoRecasting using R Forecasting the PBS 6 Total cost: A03 concession safety net group Time $ thousands 1995 2000 2005 0 200 400 600 800 1000 1200
14. PBS data Automatic FoRecasting using R Forecasting the PBS 6 Total cost: A05 general copayments group Time $ thousands 1995 2000 2005 0 50 100 150 200
15. PBS data Automatic FoRecasting using R Forecasting the PBS 6 Total cost: D01 general copayments group Time $ thousands 1995 2000 2005 0 100 200 300 400 500 600 700
16. PBS data Automatic FoRecasting using R Forecasting the PBS 6 Total cost: S01 general copayments group Time $ thousands 1995 2000 2005 0 500 1000 1500
17. PBS data Automatic FoRecasting using R Forecasting the PBS 6 Total cost: R03 general copayments group Time $ thousands 1995 2000 2005 1000 2000 3000 4000 5000
18. Outline 1 Forecasting the PBS 2 Exponential smoothing 3 ARIMA models 4 TBATS models 5 Hierarchical time series Automatic FoRecasting using R Exponential smoothing 7
19. Exponential smoothing methods Seasonal Component Trend N A M Component (None) (Additive) (Multiplicative) N (None) N,N N,A N,M A (Additive) A,N A,A A,M Ad (Additive damped) Ad,N Ad,A Ad,M Automatic FoRecasting using R Exponential smoothing 8
20. Exponential smoothing methods Seasonal Component Trend N A M Component (None) (Additive) (Multiplicative) N (None) N,N N,A N,M A (Additive) A,N A,A A,M Ad (Additive damped) Ad,N Ad,A Ad,M N,N: Simple exponential smoothing Automatic FoRecasting using R Exponential smoothing 8
21. Exponential smoothing methods Seasonal Component Trend N A M Component (None) (Additive) (Multiplicative) N (None) N,N N,A N,M A (Additive) A,N A,A A,M Ad (Additive damped) Ad,N Ad,A Ad,M N,N: Simple exponential smoothing A,N: Holt’s linear method Automatic FoRecasting using R Exponential smoothing 8
22. Exponential smoothing methods Seasonal Component Trend N A M Component (None) (Additive) (Multiplicative) N (None) N,N N,A N,M A (Additive) A,N A,A A,M Ad (Additive damped) Ad,N Ad,A Ad,M N,N: Simple exponential smoothing A,N: Holt’s linear method Ad,N: Additive damped trend method Automatic FoRecasting using R Exponential smoothing 8
23. Exponential smoothing methods Seasonal Component Trend N A M Component (None) (Additive) (Multiplicative) N (None) N,N N,A N,M A (Additive) A,N A,A A,M Ad (Additive damped) Ad,N Ad,A Ad,M N,N: Simple exponential smoothing A,N: Holt’s linear method Ad,N: Additive damped trend method A,A: Additive Holt-Winters’ method Automatic FoRecasting using R Exponential smoothing 8
24. Exponential smoothing methods Seasonal Component Trend N A M Component (None) (Additive) (Multiplicative) N (None) N,N N,A N,M A (Additive) A,N A,A A,M Ad (Additive damped) Ad,N Ad,A Ad,M N,N: Simple exponential smoothing A,N: Holt’s linear method Ad,N: Additive damped trend method A,A: Additive Holt-Winters’ method A,M: Multiplicative Holt-Winters’ method Automatic FoRecasting using R Exponential smoothing 8
25. Exponential smoothing methods Seasonal Component Trend N A M Component (None) (Additive) (Multiplicative) N (None) N,N N,A N,M A (Additive) A,N A,A A,M Ad (Additive damped) Ad,N Ad,A Ad,M There are 9 separate exponential smoothing methods. Automatic FoRecasting using R Exponential smoothing 8
26. Exponential smoothing methods Seasonal Component Trend N A M Component (None) (Additive) (Multiplicative) N (None) N,N N,A N,M A (Additive) A,N A,A A,M Ad (Additive damped) Ad,N Ad,A Ad,M There are 9 separate exponential smoothing methods. Each can have an additive or multiplicative error, giving 18 separate models. Automatic FoRecasting using R Exponential smoothing 8
27. Exponential smoothing methods Seasonal Component Trend N A M Component (None) (Additive) (Multiplicative) N (None) N,N N,A N,M A (Additive) A,N A,A A,M Ad (Additive damped) Ad,N Ad,A Ad,M There are 9 separate exponential smoothing methods. Each can have an additive or multiplicative error, giving 18 separate models. Only 15 models are numerically stable. Automatic FoRecasting using R Exponential smoothing 8
28. Cross-validation Traditional evaluation Automatic FoRecasting using R Exponential smoothing 9 q q q q q q q q q q q q q q q q q q q q q q q q q time Training data Test data
29. Cross-validation Traditional evaluation Standard cross-validation Automatic FoRecasting using R Exponential smoothing 9 q q q q q q q q q q q q q q q q q q q q q q q q q time Training data Test data q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q
30. Cross-validation Traditional evaluation Standard cross-validation Time series cross-validation Automatic FoRecasting using R Exponential smoothing 9 q q q q q q q q q q q q q q q q q q q q q q q q q time Training data Test data q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q
31. Cross-validation Traditional evaluation Standard cross-validation Time series cross-validation Automatic FoRecasting using R Exponential smoothing 9 q q q q q q q q q q q q q q q q q q q q q q q q q time Training data Test data q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q
32. Cross-validation Traditional evaluation Standard cross-validation Time series cross-validation Automatic FoRecasting using R Exponential smoothing 9 q q q q q q q q q q q q q q q q q q q q q q q q q time Training data Test data q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q Also known as “Evaluation on a rolling forecast origin”
33. Akaike’s Information Criterion AICC = −2 log(L) + 2k + 2(k + 1)(k + 2) T − k where L is the likelihood, k is the number of estimated parameters in the model and T is the number of observations in the series. Minimizing the Gaussian AIC is asymptotically equivalent (as T → ∞) to minimizing MSE from one-step forecasts on test set via time series cross-validation. Automatic FoRecasting using R Exponential smoothing 10
34. Akaike’s Information Criterion AICC = −2 log(L) + 2k + 2(k + 1)(k + 2) T − k where L is the likelihood, k is the number of estimated parameters in the model and T is the number of observations in the series. Minimizing the Gaussian AIC is asymptotically equivalent (as T → ∞) to minimizing MSE from one-step forecasts on test set via time series cross-validation. Automatic FoRecasting using R Exponential smoothing 10
35. ets algorithm in R Automatic FoRecasting using R Exponential smoothing 11 Based on Hyndman, Koehler, Snyder & Grose (IJF 2002): Apply each of 15 models that are appropriate to the data. Optimize parameters and initial values using MLE. Select best method using AICc. Produce forecasts using best method. Obtain prediction intervals using underlying state space model.
36. ets algorithm in R Automatic FoRecasting using R Exponential smoothing 11 Based on Hyndman, Koehler, Snyder & Grose (IJF 2002): Apply each of 15 models that are appropriate to the data. Optimize parameters and initial values using MLE. Select best method using AICc. Produce forecasts using best method. Obtain prediction intervals using underlying state space model.
37. ets algorithm in R Automatic FoRecasting using R Exponential smoothing 11 Based on Hyndman, Koehler, Snyder & Grose (IJF 2002): Apply each of 15 models that are appropriate to the data. Optimize parameters and initial values using MLE. Select best method using AICc. Produce forecasts using best method. Obtain prediction intervals using underlying state space model.
38. ets algorithm in R Automatic FoRecasting using R Exponential smoothing 11 Based on Hyndman, Koehler, Snyder & Grose (IJF 2002): Apply each of 15 models that are appropriate to the data. Optimize parameters and initial values using MLE. Select best method using AICc. Produce forecasts using best method. Obtain prediction intervals using underlying state space model.
39. Exponential smoothing Automatic FoRecasting using R Exponential smoothing 12 300 400 500 600 1960 1980 2000 Year Number of sheep (millions) level 80 95 Forecasts from ETS(M,A,N)
40. Exponential smoothing Automatic FoRecasting using R Exponential smoothing 13 300 400 500 600 1960 1980 2000 Year Number of sheep (millions) level 80 95 Forecasts from ETS(M,A,N) fit <- ets(livestock) fcast <- forecast(fit) plot(fcast)
41. Exponential smoothing Automatic FoRecasting using R Exponential smoothing 14 0.3 0.6 0.9 1.2 1.5 1995 2000 2005 2010 Year millions of scripts level 80 95 Forecasts from ETS(M,Ad,M)
42. Exponential smoothing Automatic FoRecasting using R Exponential smoothing 15 0.3 0.6 0.9 1.2 1.5 1995 2000 2005 2010 Year millions of scripts level 80 95 Forecasts from ETS(M,Ad,M) fit <- ets(h02) fcast <- forecast(fit) plot(fcast)
43. Outline 1 Forecasting the PBS 2 Exponential smoothing 3 ARIMA models 4 TBATS models 5 Hierarchical time series Automatic FoRecasting using R ARIMA models 16
44. auto.arima algorithm in R Based on Hyndman and Khandakar (JSS 2008): Select no. differences via unit root tests. Use stepwise search to traverse model space, starting with a simple model and considering nearby variants. For each model, optimize parameters using MLE. Select best method using AICc. Produce forecasts and prediction intervals using best method. Automatic FoRecasting using R ARIMA models 17
45. auto.arima algorithm in R Based on Hyndman and Khandakar (JSS 2008): Select no. differences via unit root tests. Use stepwise search to traverse model space, starting with a simple model and considering nearby variants. For each model, optimize parameters using MLE. Select best method using AICc. Produce forecasts and prediction intervals using best method. Automatic FoRecasting using R ARIMA models 17
46. auto.arima algorithm in R Based on Hyndman and Khandakar (JSS 2008): Select no. differences via unit root tests. Use stepwise search to traverse model space, starting with a simple model and considering nearby variants. For each model, optimize parameters using MLE. Select best method using AICc. Produce forecasts and prediction intervals using best method. Automatic FoRecasting using R ARIMA models 17
47. auto.arima algorithm in R Based on Hyndman and Khandakar (JSS 2008): Select no. differences via unit root tests. Use stepwise search to traverse model space, starting with a simple model and considering nearby variants. For each model, optimize parameters using MLE. Select best method using AICc. Produce forecasts and prediction intervals using best method. Automatic FoRecasting using R ARIMA models 17
48. auto.arima algorithm in R Based on Hyndman and Khandakar (JSS 2008): Select no. differences via unit root tests. Use stepwise search to traverse model space, starting with a simple model and considering nearby variants. For each model, optimize parameters using MLE. Select best method using AICc. Produce forecasts and prediction intervals using best method. Automatic FoRecasting using R ARIMA models 17
49. Auto ARIMA Automatic FoRecasting using R ARIMA models 18 300 400 500 1960 1980 2000 Year Number of sheep (millions) level 80 95 Forecasts from ARIMA(0,1,0) with drift
50. Auto ARIMA Automatic FoRecasting using R ARIMA models 19 300 400 500 1960 1980 2000 Year Number of sheep (millions) level 80 95 Forecasts from ARIMA(0,1,0) with drift fit <- auto.arima(livestock) fcast <- forecast(fit) plot(fcast)
51. Auto ARIMA Automatic FoRecasting using R ARIMA models 20 0.3 0.6 0.9 1.2 1995 2000 2005 2010 Year millions of scripts level 80 95 Forecasts from ARIMA(3,1,3)(0,1,1)[12]
52. Auto ARIMA Automatic FoRecasting using R ARIMA models 21 0.3 0.6 0.9 1.2 1995 2000 2005 2010 Year millions of scripts level 80 95 Forecasts from ARIMA(3,1,3)(0,1,1)[12] fit <- auto.arima(h02) fcast <- forecast(fit) plot(fcast)
53. Outline 1 Forecasting the PBS 2 Exponential smoothing 3 ARIMA models 4 TBATS models 5 Hierarchical time series Automatic FoRecasting using R TBATS models 22
54. TBATS model TBATS Trigonometric terms for seasonality Box-Cox transformations for heterogeneity ARMA errors for short-term dynamics Trend (possibly damped) Seasonal (including multiple and non-integer periods) Automatic algorithm described in De Livera, Hyndman and Snyder (JASA 2011). Automatic FoRecasting using R TBATS models 23
55. Examples Automatic FoRecasting using R TBATS models 24 7 8 9 10 1995 2000 2005 Year Thousands of barrels level 80 95 Forecasts from TBATS(1, {0,0}, 1, {<52.1785714285714,9>}) fit <- tbats(gas) fcast <- forecast(fit) plot(fcast)
56. Examples Automatic FoRecasting using R TBATS models 25 0 200 400 0 10 20 30 Weeks Number of calls level 80 95 Forecasts from TBATS(0.607, {0,0}, −, {<169,5>, <845,4>}) fit <- tbats(callcentre) fcast <- forecast(fit) plot(fcast)
57. Outline 1 Forecasting the PBS 2 Exponential smoothing 3 ARIMA models 4 TBATS models 5 Hierarchical time series Automatic FoRecasting using R Hierarchical time series 26
58. Hierarchical time series A hierarchical time series is a collection of several time series that are linked together in a hierarchical structure. Total A AA AB AC B BA BB BC C CA CB CC Examples Manufacturing product hierarchies Sales by state and region Automatic FoRecasting using R Hierarchical time series 27
59. Hierarchical time series A hierarchical time series is a collection of several time series that are linked together in a hierarchical structure. Total A AA AB AC B BA BB BC C CA CB CC Examples Manufacturing product hierarchies Sales by state and region Automatic FoRecasting using R Hierarchical time series 27
60. Hierarchical time series A hierarchical time series is a collection of several time series that are linked together in a hierarchical structure. Total A AA AB AC B BA BB BC C CA CB CC Examples Manufacturing product hierarchies Sales by state and region Automatic FoRecasting using R Hierarchical time series 27
61. Optimal reconciliation Traditional approaches: Bottom-up Top-down Middle-out A better way: 1 Forecast all series at all levels of aggregation. 2 Reconcile the forecasts by making the smallest possible changes such that they add up. 3 Extremely fast algorithm implemented in the hts package for R. Automatic FoRecasting using R Hierarchical time series 28
62. Optimal reconciliation Traditional approaches: Bottom-up Top-down Middle-out A better way: 1 Forecast all series at all levels of aggregation. 2 Reconcile the forecasts by making the smallest possible changes such that they add up. 3 Extremely fast algorithm implemented in the hts package for R. Automatic FoRecasting using R Hierarchical time series 28
63. Optimal reconciliation Traditional approaches: Bottom-up Top-down Middle-out A better way: 1 Forecast all series at all levels of aggregation. 2 Reconcile the forecasts by making the smallest possible changes such that they add up. 3 Extremely fast algorithm implemented in the hts package for R. Automatic FoRecasting using R Hierarchical time series 28
64. Optimal reconciliation Traditional approaches: Bottom-up Top-down Middle-out A better way: 1 Forecast all series at all levels of aggregation. 2 Reconcile the forecasts by making the smallest possible changes such that they add up. 3 Extremely fast algorithm implemented in the hts package for R. Automatic FoRecasting using R Hierarchical time series 28
65. Optimal reconciliation Traditional approaches: Bottom-up Top-down Middle-out A better way: 1 Forecast all series at all levels of aggregation. 2 Reconcile the forecasts by making the smallest possible changes such that they add up. 3 Extremely fast algorithm implemented in the hts package for R. Automatic FoRecasting using R Hierarchical time series 28
66. Optimal reconciliation Traditional approaches: Bottom-up Top-down Middle-out A better way: 1 Forecast all series at all levels of aggregation. 2 Reconcile the forecasts by making the smallest possible changes such that they add up. 3 Extremely fast algorithm implemented in the hts package for R. Automatic FoRecasting using R Hierarchical time series 28
67. Optimal reconciliation Traditional approaches: Bottom-up Top-down Middle-out A better way: 1 Forecast all series at all levels of aggregation. 2 Reconcile the forecasts by making the smallest possible changes such that they add up. 3 Extremely fast algorithm implemented in the hts package for R. Automatic FoRecasting using R Hierarchical time series 28
68. Australian tourism Automatic FoRecasting using R Hierarchical time series 29
69. Australian tourism Automatic FoRecasting using R Hierarchical time series 29 Hierarchy: States (7) Zones (27) Regions (82)
70. Australian tourism Automatic FoRecasting using R Hierarchical time series 29 Hierarchy: States (7) Zones (27) Regions (82) Base forecasts ETS (exponential smoothing) models
71. Base forecasts Automatic FoRecasting using R Hierarchical time series 30 Domestic tourism forecasts: Total Year Visitor nights 1998 2000 2002 2004 2006 2008 60000 65000 70000 75000 80000 85000
72. Base forecasts Automatic FoRecasting using R Hierarchical time series 30 Domestic tourism forecasts: NSW Year Visitor nights 1998 2000 2002 2004 2006 2008 18000 22000 26000 30000
73. Base forecasts Automatic FoRecasting using R Hierarchical time series 30 Domestic tourism forecasts: VIC Year Visitor nights 1998 2000 2002 2004 2006 2008 10000 12000 14000 16000 18000
74. Base forecasts Automatic FoRecasting using R Hierarchical time series 30 Domestic tourism forecasts: Nth.Coast.NSW Year Visitor nights 1998 2000 2002 2004 2006 2008 5000 6000 7000 8000 9000
75. Base forecasts Automatic FoRecasting using R Hierarchical time series 30 Domestic tourism forecasts: Metro.QLD Year Visitor nights 1998 2000 2002 2004 2006 2008 8000 9000 11000 13000
76. Base forecasts Automatic FoRecasting using R Hierarchical time series 30 Domestic tourism forecasts: Sth.WA Year Visitor nights 1998 2000 2002 2004 2006 2008 400 600 800 1000 1200 1400
77. Base forecasts Automatic FoRecasting using R Hierarchical time series 30 Domestic tourism forecasts: X201.Melbourne Year Visitor nights 1998 2000 2002 2004 2006 2008 4000 4500 5000 5500 6000
78. Base forecasts Automatic FoRecasting using R Hierarchical time series 30 Domestic tourism forecasts: X402.Murraylands Year Visitor nights 1998 2000 2002 2004 2006 2008 0 100 200 300
79. Base forecasts Automatic FoRecasting using R Hierarchical time series 30 Domestic tourism forecasts: X809.Daly Year Visitor nights 1998 2000 2002 2004 2006 2008 0 20 40 60 80 100
80. Reconciled forecasts Automatic FoRecasting using R Hierarchical time series 31 Total 2000 2005 2010 65000 80000 95000
81. Reconciled forecasts Automatic FoRecasting using R Hierarchical time series 31 NSW 2000 2005 2010 18000 24000 30000 VIC 2000 2005 2010 10000 14000 18000 QLD 2000 2005 2010 14000 20000 Other 2000 2005 2010 18000 24000
82. Reconciled forecasts Automatic FoRecasting using R Hierarchical time series 31 Sydney 2000 2005 2010 4000 7000 Other NSW 2000 2005 2010 14000 22000 Melbourne 2000 2005 2010 4000 5000 Other VIC 2000 2005 2010 6000 12000 GC and Brisbane 2000 2005 2010 6000 9000 Other QLD 2000 2005 2010 6000 12000 Capital cities 2000 2005 2010 14000 20000 Other 2000 2005 2010 5500 7500
83. Forecast evaluation Select models using all observations; Re-estimate models using first 12 observations and generate 1- to 8-step-ahead forecasts; Increase sample size one observation at a time, re-estimate models, generate forecasts until the end of the sample; In total 24 1-step-ahead, 23 2-steps-ahead, up to 17 8-steps-ahead for forecast evaluation. Automatic FoRecasting using R Hierarchical time series 32
84. Forecast evaluation Select models using all observations; Re-estimate models using first 12 observations and generate 1- to 8-step-ahead forecasts; Increase sample size one observation at a time, re-estimate models, generate forecasts until the end of the sample; In total 24 1-step-ahead, 23 2-steps-ahead, up to 17 8-steps-ahead for forecast evaluation. Automatic FoRecasting using R Hierarchical time series 32
85. Forecast evaluation Select models using all observations; Re-estimate models using first 12 observations and generate 1- to 8-step-ahead forecasts; Increase sample size one observation at a time, re-estimate models, generate forecasts until the end of the sample; In total 24 1-step-ahead, 23 2-steps-ahead, up to 17 8-steps-ahead for forecast evaluation. Automatic FoRecasting using R Hierarchical time series 32
86. Forecast evaluation Select models using all observations; Re-estimate models using first 12 observations and generate 1- to 8-step-ahead forecasts; Increase sample size one observation at a time, re-estimate models, generate forecasts until the end of the sample; In total 24 1-step-ahead, 23 2-steps-ahead, up to 17 8-steps-ahead for forecast evaluation. Automatic FoRecasting using R Hierarchical time series 32
87. Hierarchy: states, zones, regions MAPE h = 1 h = 2 h = 4 h = 6 h = 8 Average Top Level: Australia Bottom-up 3.79 3.58 4.01 4.55 4.24 4.06 OLS 3.83 3.66 3.88 4.19 4.25 3.94 WLS 3.68 3.56 3.97 4.57 4.25 4.04 Level: States Bottom-up 10.70 10.52 10.85 11.46 11.27 11.03 OLS 11.07 10.58 11.13 11.62 12.21 11.35 WLS 10.44 10.17 10.47 10.97 10.98 10.67 Level: Zones Bottom-up 14.99 14.97 14.98 15.69 15.65 15.32 OLS 15.16 15.06 15.27 15.74 16.15 15.48 WLS 14.63 14.62 14.68 15.17 15.25 14.94 Bottom Level: Regions Bottom-up 33.12 32.54 32.26 33.74 33.96 33.18 OLS 35.89 33.86 34.26 36.06 37.49 35.43 WLS 31.68 31.22 31.08 32.41 32.77 31.89 Automatic FoRecasting using R Hierarchical time series 33
88. Forecast package history Pre 2003 Collection of functions used for consulting projects July/August 2003 ets and thetaf added August 2006 v1.0 available on CRAN May 2007 auto.arima added July 2008 JSS paper (Hyndman & Khandakar) September 2009 v2.0. Unbundled. May 2010 arfima added Feb/March 2011 tslm, stlf, naive, snaive added August 2011 v3.0. Box Cox transformations added December 2011 tbats added April 2012 Package moved to github November 2012 v4.0. nnetar added June 2013 Major speed-up of ets January 2014 v5.0. tsoutliers and tsclean added May 2015 v6.0. Added several new plots December 2015 264,000 package downloads in one month! February 2016 v7.0. Added ggplot2 graphics & bias adjustment Automatic FoRecasting using R Hierarchical time series 34
89. For further information robjhyndman.com Slides for this talk. Links to all papers and books. Links to R packages. A blog about forecasting research. OTexts.org/fpp Free online book based on forecast package for R. Automatic FoRecasting using R Hierarchical time series 35