Abstract

Electricity and electric-equipment play a critical role in modern living, and precise price forecasting for these items’ aids decision-makers in anticipating changes, planning, and budgeting ahead of time. This present research focused on the wholesale price indexes of items from the "manufacture of electrical equipment (MEEQ)" group of India's existing wholesale price index (WPI) series. This work proposed a novel, state-of-art ensemble forecast approach that used multilayer perceptron (MLP) and Holt's linear (HL) approaches for some specified WPIs from this group. The researchers selected the WPIs that manifest non-linearity as determined by the curve-fit technique. The paper applied a variance-based weighted average scheme to generate the ensemble forecast. The statistical rigor-based curve-fit aided in identifying that seventeen out of forty-eight indexes manifest non-linear fits. The proposed MLP-HL ensemble approach exhibited excellent forecast results (relative root mean squared error, i.e., RRMSE < 10%) for all seventeen WPIs. For each of these seventeen WPI's, the current work compared the proposed MLP-HL with nineteen models (eight statistical, four machine learning, and seven contemporary ensemble strategies). In the majority of the cases, it outran the nineteen models in terms of mean absolute error (MAE) and the mean absolute percentage error (MAPE). As an alternative pathway for forecasting these seventeen non-linear WPIs, the present work suggests using this proposed MLP-HL approach.

Keyword

Curve-fit, Multilayer perceptron, Holt’s linear, Ensemble forecasting, Wholesale price index.

Cite this article

Das D, Chakrabarti S

Refference

[1][1]https://data.gov.in/resources/wholesale-price-index-base-year-2011-12-upto-may-2017. Accessed 10 March 2021.

[2][2]Mgale YJ, Yan Y, Timothy S. A comparative study of ARIMA and holt-winters exponential smoothing models for rice price forecasting in Tanzania. Open Access Library Journal. 2021; 8(5):1-9.

[3][3]Rachmat R, Suhartono S. Comparative analysis of single exponential smoothing and holts method for quality of hospital services forecasting in general hospital. Bulletin of Computer Science and Electrical Engineering. 2020; 1(2):80-6.

[4][4]Yonar H, Yonar A, Tekindal MA, Tekindal M. Modeling and forecasting for the number of cases of the COVID-19 pandemic with the curve estimation models, the box-jenkins and exponential smoothing methods. EJMO. 2020; 4(2):160-5.

[5][5]Şahinli MA. Potato price forecasting with Holt-Winters and ARIMA methods: a case study. American Journal of Potato Research. 2020; 97(4):336-46.

[6][6]Iruela JR, Ruiz LG, Capel MI, Pegalajar MC. A tensorflow approach to data analysis for time series forecasting in the energy-efficiency realm. Energies. 2021; 14(13):1-22.

[7][7]Bhardwaj S, Chandrasekhar E, Padiyar P, Gadre VM. A comparative study of wavelet-based ANN and classical techniques for geophysical time-series forecasting. Computers & Geosciences. 2020.

[8][8]Deina C, Do APMH, Alves CH, Martins MS, Trojan F, Stevan JSL, et al. A methodology for coffee price forecasting based on extreme learning machines. Information Processing in Agriculture. 2021.

[9][9]Waheeb W, Shah H, Jabreel M, Puig D. Bitcoin price forecasting: a comparative study between statistical and machine learning methods. In international conference on computer and information sciences 2020 (pp. 1-5). IEEE.

[10][10]Jha BK, Pande S. Time series forecasting model for supermarket sales using FB-prophet. In 5th international conference on computing methodologies and communication 2021(pp. 547-54). IEEE.

[11][11]Madhuri CR, Chinta M, Kumar VP. Stock market prediction for time-series forecasting using prophet upon ARIMA. In international conference on smart structures and systems 2020 (pp. 1-5). IEEE.

[12][12]Harahap LA, Lipikorn R, Kitamoto A. Nikkei stock market price index prediction using machine learning. In journal of physics: conference series 2020 (pp. 1-5). IOP Publishing.

[13][13]Zheng J, Wang Y, Li S, Chen H. The stock index prediction based on SVR model with bat optimization algorithm. Algorithms. 2021; 14(10):1-31.

[14][14]Gastinger J, Nicolas S, Stepić D, Schmidt M, Schülke A. A study on ensemble learning for time series forecasting and the need for meta-learning. In international joint conference on neural networks 2021 (pp. 1-8). IEEE.

[15][15]Tyralis H, Papacharalampous G, Langousis A. Super ensemble learning for daily streamflow forecasting: large-scale demonstration and comparison with multiple machine learning algorithms. Neural Computing and Applications. 2021; 33(8):3053-68.

[16][16]Kaushik S, Choudhury A, Sheron PK, Dasgupta N, Natarajan S, Pickett LA, et al. AI in healthcare: time-series forecasting using statistical, neural, and ensemble architectures. Frontiers in Big Data. 2020; 3(4):1-17.

[17][17]Jibrin SA, Musa Y, Samaila M, Abdul A. Comparing the performance of ARIMA and ARFURIMA model in forecasting Nigeria stock price index. SLU Journal of Science and Technology. 2021; 2(2):1-5.

[18][18]Challa ML, Malepati V, Kolusu SN. S&P BSE sensex and S&P bse it return forecasting using arima. Financial Innovation. 2020; 6(1):1-19.

[19][19]Ghazo A. Applying the ARIMA model to the process of forecasting GDP and CPI in the Jordanian Economy. International Journal of Financial Research. 2021; 12(3):70-7.

[20][20]Mohamed J. Time series modeling and forecasting of Somaliland consumer price index: a comparison of ARIMA and regression with ARIMA errors. American Journal of Theoretical and Applied Statistics. 2020; 9(4):143-53.

[21][21]Das P, Jha GK, Lama A, Parsad R, Mishra D. Empirical mode decomposition based support vector regression for agricultural price forecasting. Indian Journal of Extension Education. 2020; 56(2): 7-12.

[22][22]Patra S. Time series analysis and forecast of India’s wholesale price index inflation. In applied research international conferences 2018 (pp. 5-17).

[23][23]Das D. Data mining of Indian stock market from April, 2015 to March, 2016 using curve fitting technique. International Research Journal of Engineering and Technology (IRJET). 2016; 3(05):2564-70.

[24][24]Das D, Chakrabarti P. Does the pattern of wholesale price index of India changes every year in the last ten years-what curves tells us. International Journal of Engineering and Management Research (IJEMR). 2015; 5(2):723-8.

[25][25]Juarna A, Kuswanto A, Mukhyi MA, Supriyanto R. Curve fitting and stock price prediction using least square method. Detail. 2015; 2(2).

[26][26]Juarna A. One year stock price prediction and its validity using least square method in Matlab. International Journal of Advanced Research. 2017; 5(2): 1641-8.

[27][27]https://www.esri.com/arcgis-blog/products/arcgis-pro/analytics/time-series-forecasting-101-part-3-forecast-covid-19-cumulative-confirmed-cases-with-curve-fit-forecast-and-evaluate-forecasts-by-location/. Accessed 1 October 2021.

[28][28]https://medium.com/analytics-vidhya/how-to-predict-when-the-covid-19-pandemic-will-stop-in-your-country-with-python-d6fbb2425a9f. Accessed 1 October 2021.

[29][29]Klosterman RE, Brooks K, Drucker J, Feser E, Renski H. Planning support methods: urban and regional analysis and projection. Rowman & Littlefield; 2018.

[30][30]Banerjee A. Forecasting price levels in India–an Arima framework. Academy of Marketing Studies Journal. 2021; 25(1):1-5.

[31][31]Nyoni T. ARIMA modeling and forecasting of consumer price index (CPI) in Germany. Munich Personal RePEc Archive.2019.

[32][32]Dutta S, Maiti S. Price forecasting of agricultural products using Arima models. Indian Journal of Agricultural Marketing. 2021; 35(2):149-64.

[33][33]Jamuna CJ, Patil C, Kumar RA. Forecasting the price of potato using time series ARIMA Model. In proceedings of international conference on communication and computational technologies 2021 (pp. 493-518). Springer, Singapore.

[34][34]Bolarinwa IA, Bolarinwa BT. Understanding features of time series through exponential smoothing. International Journal of Advanced Academic Research. 2021; 7(8):15-9.

[35][35]Shukor SA, Sufahani SF, Khalid K, Abd WMH, Idrus SZ, Ahmad A, et al. Forecasting stock market price of gold, silver, crude oil and platinum by using double exponential smoothing, holt’s linear trend and random walk. In journal of physics: conference series 2021 (pp. 1-12). IOP Publishing.

[36][36]Khamis A, Awang NS. Forecasting kijang emas price using holt-tend exponential smoothing and ARIMA model. International Journal for Research in Applied Science and Engineering Technology. 2020; 8(8):1531-9.

[37][37]Al-sultan A, Al-rubkhi A, Alsaber A, Pan J. Forecasting air passenger traffic volume: evaluating time series models in long-term forecasting of Kuwait air passenger data. Advances and Applications in Statistics. 2021; 70(1):69-89.

[38][38]Murali M, Srinivasan R. Forecasting Covid-19 confirmed cases in India with snaive, ETS, ARIMA methods. Bulletin Monumental. 2020; 21(9):27-35.

[39][39]Sun Z. Comparison of trend forecast using ARIMA and ETS models for S&P500 close price. In 2020 the 4th international conference on e-business and internet 2020 (pp. 57-60).

[40][40]Maryasin OY, Lukashov AI. Analyzing and forecasting peak load hours. In international conference on industrial engineering, applications and manufacturing 2021 (pp. 25-30). IEEE.

[41][41]Babazadeh R, Shamsi M, Shafipour F. Optimum prediction and forecasting of wheat demand in Iran. International Journal of Applied Management Science. 2021; 13(2):141-51.

[42][42]Zhang H, Nguyen H, Vu DA, Bui XN, Pradhan B. Forecasting monthly copper price: a comparative study of various machine learning-based methods. Resources Policy. 2021.

[43][43]Alegado RT, Tumibay GM. Statistical and machine learning methods for vaccine demand forecasting: a comparative analysis. Journal of Computer and Communications. 2020; 8(10):37-49.

[44][44]Lorente-Leyva LL, Alemany MM, Peluffo-Ordóñez DH, Herrera-Granda ID. A Comparison of machine learning and classical demand forecasting methods: a case study of Ecuadorian textile industry. In international conference on machine learning, optimization, and data science 2020 (pp. 131-42). Springer, Cham.

[45][45]Puchalsky W, Ribeiro GT, Da VCP, Freire RZ, Dos SCL. Agribusiness time series forecasting using Wavelet neural networks and metaheuristic optimization: an analysis of the soybean sack price and perishable products demand. International Journal of Production Economics. 2018; 203:174-89.

[46][46]Syriopoulos T, Tsatsaronis M, Karamanos I. Support vector machine algorithms: an application to ship price forecasting. Computational Economics. 2021; 57(1):55-87.

[47][47]Wu J, Wang YG, Tian YC, Burrage K, Cao T. Support vector regression with asymmetric loss for optimal electric load forecasting. Energy. 2021.

[48][48]Bathla G. Stock price prediction using LSTM and SVR. In sixth international conference on parallel, distributed and grid computing 2020 (pp. 211-4). IEEE.

[49][49]Rostami-tabar B, Rendon-sanchez JF. Forecasting COVID-19 daily cases using phone call data. Applied Soft Computing. 2021.

[50][50]Riofrío J, Chang O, Revelo-fuelagán EJ, Peluffo-ordóñez DH. Forecasting the consumer price index (cpi) of ecuador: a comparative study of predictive models. International Journal on Advanced Science, Engineering and Information Technology. 2020; 10(3):1078-84.

[51][51]Galicia A, Talavera-llames R, Troncoso A, Koprinska I, Martínez-alvarez F. Multi-step forecasting for big data time series based on ensemble learning. Knowledge-Based Systems. 2019; 163:830-41.

[52][52]Li J, Hao J, Feng Q, Sun X, Liu M. Optimal selection of heterogeneous ensemble strategies of time series forecasting with multi-objective programming. Expert Systems with Applications. 2021.

[53][53]Shastri S, Singh K, Deswal M, Kumar S, Mansotra V. CoBiD-net: a tailored deep learning ensemble model for time series forecasting of Covid-19. Spatial Information Research. 2022; 30(1):9-22.

[54][54]Wang J, He J, Feng C, Feng L, Li Y. Stock index prediction and uncertainty analysis using multi-scale nonlinear ensemble paradigm of optimal feature extraction, two-stage deep learning and Gaussian process regression. Applied Soft Computing. 2021.

[55][55]Lin Y, Yan Y, Xu J, Liao Y, Ma F. Forecasting stock index price using the CEEMDAN-LSTM model. The North American Journal of Economics and Finance. 2021.

[56][56]Ribeiro MH, Dos SCL. Ensemble approach based on bagging, boosting and stacking for short-term prediction in agribusiness time series. Applied Soft Computing. 2020.

[57][57]Despotovic M, Nedic V, Despotovic D, Cvetanovic S. Evaluation of empirical models for predicting monthly mean horizontal diffuse solar radiation. Renewable and Sustainable Energy Reviews. 2016; 56:246-60.

[58][58]Saba T, Abunadi I, Shahzad MN, Khan AR. Machine learning techniques to detect and forecast the daily total Covid‐19 infected and deaths cases under different lockdown types. Microscopy Research and Technique. 2021; 84(7):1462-74.

[59][59]Team RC. R: a language and environment for statistical computing. 2013.

[60][60]Bertolaccini L, Solli P, Pardolesi A, Pasini A. An overview of the use of artificial neural networks in lung cancer research. Journal of Thoracic Disease. 2017; 9(4):924-31.

[61][61]https://towardsdatascience.com/introduction-to-neural-networks-advantages-and-applications-96851bd1a207. Accessed 1 October 2021.

[62][62]https://otexts.com/fpp2/holt.html. Accessed 3 October 2021.

[63][63]Raviv E. Forecastcombinations: forecast combinations in R. R Package Version 1.1.2015.

[64][64]Perone G. Comparison of ARIMA, ETS, NNAR, TBATS and hybrid models to forecast the second wave of COVID-19 hospitalizations in Italy. The European Journal of Health Economics. 2021; 23(6):1917-40.

[65][65]Perone G. An ARIMA model to forecast the spread and the final size of Covid-2019 epidemic in Italy. MedRxiv. 2020.

[66][66]Kumar P. Forecasting cloud resource utilization using time series methods. Digitala Vetenskapliga Arkivet. 2018.

[67][67]Sreeram L, Sayed SA. Short-term forecasting ability of hybrid models for BRIC currencies. Global Business Review. 2020.

[68][68]Shaub D. Fast and accurate yearly time series forecasting with forecast combinations. International Journal of Forecasting. 2020; 36(1):116-20.

[69][69]https://pkg.robjhyndman.com/forecast/. Accessed 3 October 2021.

[70][70]Hyndman RJ, Khandakar Y. Automatic time series forecasting: the forecast package for R. Journal of Statistical Software. 2008; 27:1-22.

[71][71]Kourentzes N. Nnfor: time series forecasting with neural networks. R Package. 2017.

[72][72]Taylor SJ, Letham B. Forecasting at scale. The American Statistician. 2018; 72(1):37-45.

[73][73]Meyer D, Dimitriadou E, Hornik K, Weingessel A, Leisch F, Chang CC, et al. e1071: Misc functions of the department of statistics, probability theory group (Formerly: E1071), TU Wien [R Package Version 1.7-9]. Comprehensive R Archive Network (CRAN). 2021.

[74][74]https://CRAN.R-project.org/package=forecastHybrid. Accessed 3 October 2021.

[75][75]Phuruan K, Kasemset C. Shallot price forecasting model using hybrid ARIMA-LSTM model. Data Science and Engineering (DSE).3(1):35-43.

[76][76]Arslan S. A hybrid forecasting model using LSTM and prophet for energy consumption with decomposition of time series data. Peer J Computer Science. 2022.