Sistem Analisis Transaksi Tunai Harian Kenna Cell Menggunakan Machine Learning: Kenna Cell Daily Cash Transaction Analysis System Using Machine Learning

Niken Ayu Ambarwati; Andy Prasetyo Utomo; Supriyono Supriyono

doi:10.57152/malcom.v6i4.3063

Authors

Niken Ayu Ambarwati Universitas Muria Kudus
Andy Prasetyo Utomo Universitas Muria Kudus
Supriyono Supriyono Universitas Muria Kudus

DOI:

https://doi.org/10.57152/malcom.v6i4.3063

Keywords:

Arus Kas, CatBoost, CRISP-DM, Machine Learning, Prediksi Likuiditas

Abstract

Analisis transaksi tunai harian menjadi kebutuhan penting bagi UMKM yang mencatat transaksi melalui berbagai metode pembayaran digital. Kenna Cell mengelola 13.289 catatan transaksi pada delapan metode pembayaran, sehingga pemilik usaha membutuhkan analisis harian yang terstruktur untuk mengantisipasi arus keluar dan tingkat kepadatan transaksi. Penelitian ini bertujuan membangun sistem berbasis machine learning yang membersihkan data transaksi tunai, menyusun panel harian, memperkirakan nominal outflow pada hari berikutnya, dan mengelompokkan kepadatan transaksi ke dalam kategori rendah, sedang, dan tinggi. Alur penelitian mengikuti CRISP-DM melalui tahap pemahaman data, pembersihan data, feature engineering, pelatihan berbasis urutan waktu, evaluasi, dan prediksi. Tahap persiapan menghasilkan 13.289 transaksi rapi dan 3.904 data harian dengan 41 indikator. XGBoost, LightGBM, dan CatBoost dibandingkan pada tugas regresi dan klasifikasi menggunakan MAE, RMSE, MAPE, R2, akurasi, presisi, recall, F1-Score Macro, dan F1-Score Weighted. CatBoost Regressor menghasilkan kesalahan terendah dengan RMSE Rp 3.534.296,59 dan MAPE 14,50%, sedangkan CatBoost Classifier memberikan keseimbangan kelas terbaik dengan akurasi 0,8066 dan F1-Score Macro 0,7713. Kebaruan penelitian terletak pada integrasi pembentukan panel harian, regresi nominal hari berikutnya, klasifikasi kepadatan transaksi, dan prediksi berdasarkan metode pembayaran dalam satu workflow operasional berbasis web untuk UMKM. Informasi yang dihasilkan mendukung persiapan likuiditas harian secara lebih terarah, dengan tetap memerlukan verifikasi manajerial

Downloads

Download data is not yet available.

References

B. Wardana and P. N. Sitompul, “{Smart Finance}: Desain dan Implementasi Sistem Keuangan Cerdas Real-Time Berbasis {IoT} untuk {UMKM},” J. Inform. J. Pengemb. IT, vol. 11, no. 1, pp. 12–25, 2026, doi: 10.30591/jpit.v11i1.10006.

S. Malika, “Sistem Informasi Keuangan Pada {CV Abizar Group} Dengan {Statistical Analysis} Dan {Regression Model},” J. Inform. J. Pengemb. IT, vol. 11, no. 1, pp. 142–151, 2026, doi: 10.30591/jpit.v11i1.10037.

D. Bisht and others, “Imperative Role of Integrating Digitalization in the Firms Finance: A Technological Perspective,” Electronics, vol. 11, no. 19, p. 3252, 2022, doi: 10.3390/electronics11193252.

S. V Tsiu, M. Ngobeni, L. Mathabela, and B. Thango, “Applications and Competitive Advantages of Data Mining and Business Intelligence in {SMEs} Performance: A Systematic Review,” Businesses, vol. 5, no. 2, p. 22, 2025, doi: 10.3390/businesses5020022.

S. A. Hendrawan, A. Chatra, N. Iman, S. Hidayatullah, and D. Suprayitno, “Digital Transformation in {MSMEs}: Challenges and Opportunities in Technology Management,” J. Inf. dan Teknol., vol. 6, no. 2, pp. 141–149, 2024, doi: 10.60083/jidt.v6i2.551.

M. Saputra and R. M. Fadlila, “An Effective Open {ERP} System for Automation in Financial Reporting for {SMEs} Based on Service Oriented Architecture,” Int. J. Informatics Vis., vol. 7, no. 3–2, pp. 2007–2015, 2023, doi: 10.30630/joiv.7.3-2.2367.

M. Nofel, M. Marzouk, H. Elbardan, R. Saleh, and A. Mogahed, “From Sensors to Standardized Financial Reports: A Proposed Automated Accounting System Integrating {IoT}, Blockchain, and {XBRL},” J. Risk Financ. Manag., vol. 17, no. 10, p. 445, 2024, doi: 10.3390/jrfm17100445.

R. Alshahrani, A. Rizwan, M. A. Alomar, and G. Fotis, “{IoT}-Based Sustainable Energy Solutions for Small and Medium Enterprises ({SMEs}),” Energies, vol. 17, no. 16, p. 4144, 2024, doi: 10.3390/en17164144.

J. Ji, “Application and Impact Analysis of Intelligent Financial Systems in Small and Medium-Sized Manufacturing Industries,” J. Innov. Dev., vol. 7, no. 1, pp. 33–38, 2024, doi: 10.54097/29edcz69.

A. Inayah and E. D. Susliyanti, “The Impact of Cloud-Based Accounting Systems on {SME} Financial Performance in the Digital Era,” Atestasi J. Ilm. Akunt., vol. 8, no. 2, pp. 138–145, 2025, doi: 10.57178/atestasi.v8i2.1486.

F. P. Sholikah, P. Iswanto, and N. Sumarni, “Faktor-faktor Kendala dalam Pencatatan Keuangan pada {UMKM} Toko Sembako,” J. Trends Econ. Account. Res., vol. 4, no. 1, 2023, doi: 10.47065/jtear.v4i1.879.

Y. Novelidhawaty, F. G. Dewi, and U. Syaipudin, “Factors Influencing the Implementation of Accounting Digitalization in {MSMEs}: A Literature Review,” Int. J. Educ. Soc. Stud. Manag., vol. 3, no. 3, 2023, doi: 10.52121/ijessm.v3i3.186.

P. C. Verhoef et al., “Digital Transformation: A Multidisciplinary Reflection and Research Agenda,” J. Bus. Res., vol. 122, pp. 889–901, 2021, doi: 10.1016/j.jbusres.2019.09.022.

S. Kraus, P. Jones, N. Kailer, A. Weinmann, N. Chaparro-Banegas, and N. Roig-Tierno, “Digital Transformation in Business and Management Research: An Overview of the Current Status Quo,” Int. J. Inf. Manage., vol. 63, p. 102466, 2022, doi: 10.1016/j.ijinfomgt.2020.102466.

Y. Utami, M. R. Amalia, and S. Murdiati, “Optimization of Digital Finance to Improve the Performance of Klubanotic {MSMEs} in Brebes Regency,” ASEAN J. Empower. Community, vol. 3, no. 2, pp. 47–60, 2024, doi: 10.24905/ajecom/vol3issue2.64.

Ansori, N. Azizah, and F. Jaya, “Sistem Monitoring Keamanan Kamar Mandi Pintar Menggunakan {ESP32} dan Sensor {PIR} Berbasis {Internet of Things} ({IoT}),” J. Inform. J. Pengemb. IT, vol. 11, no. 2, 2026, doi: 10.30591/jpit.v11i2.10050.

N. F. Mufidah and H. H. Nuha, “Performance and Security Analysis of Lightweight Hash Functions in {IoT},” J. Inform. J. Pengemb. IT, vol. 9, no. 3, pp. 264–270, 2024, doi: 10.30591/jpit.v9i3.7633.

A. Setiyorini, “Pengembangan Aplikasi Chatbot Untuk Layanan Penerimaan Mahasiswa Baru Berbasis {Natural Language Processing},” J. Inform. J. Pengemb. IT, vol. 10, no. 4, pp. 1115–1126, 2025, doi: 10.30591/jpit.v10i4.9406.

C. Janiesch, P. Zschech, and K. Heinrich, “Machine Learning and Deep Learning,” Electron. Mark., vol. 31, pp. 685–695, 2021, doi: 10.1007/s12525-021-00475-2.

F. Petropoulos et al., “Forecasting: Theory and Practice,” Int. J. Forecast., vol. 38, no. 3, pp. 705–871, 2022, doi: 10.1016/j.ijforecast.2021.11.001.

K. Benidis et al., “Deep Learning for Time Series Forecasting: Tutorial and Literature Survey,” ACM Comput. Surv., vol. 55, no. 6, pp. 1–36, 2022, doi: 10.1145/3533382.

H. Hewamalage, C. Bergmeir, and K. Bandara, “Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions,” Int. J. Forecast., vol. 37, no. 1, pp. 388–427, 2021, doi: 10.1016/j.ijforecast.2020.06.008.

D. Chicco, N. Toetsch, and G. Jurman, “The {Matthews} Correlation Coefficient ({MCC}) Is More Reliable Than Balanced Accuracy, Bookmaker Informedness, and Markedness in Two-Class Confusion Matrix Evaluation,” PeerJ Comput. Sci., vol. 7, p. e623, 2021, doi: 10.7717/peerj-cs.623.